{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/vision-transformer/papers/ran/3","list_of":"/method/vision-transformer","method":"Vision Transformer","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":3,"pages_in_order":4,"rows_per_page":100,"rows":[201,300],"of":328,"counts":{"archive_papers_tagged":2144,"with_a_code_link":1051,"where_syntology_ran_a_sample":328,"not_listed_spam_title":0,"listed":2144,"listed_where_code_ran":328,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":286,"every_run_a_failure_of_syntologys_instrument":42,"listed_with_a_run_with_no_instrument_failure":286,"listed_every_run_a_failure_of_syntologys_instrument":42,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/vision-transformer/papers/ran/1","prev":"/method/vision-transformer/papers/ran/2","next":"/method/vision-transformer/papers/ran/4","papers":[{"paper":"/paper/protopformer-concentrating-on-prototypical","slug":"protopformer-concentrating-on-prototypical","title":"ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition","date":"2022-08-22","arxiv_id":"2208.10431","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zju-vipa/protopformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-supervised-vision-transformers-for","slug":"self-supervised-vision-transformers-for","title":"Self-Supervised Vision Transformers for Malware Detection","date":"2022-08-15","arxiv_id":"2208.07049","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sachith500/sherlock"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ghost-free-high-dynamic-range-imaging-with","slug":"ghost-free-high-dynamic-range-imaging-with","title":"Ghost-free High Dynamic Range Imaging with Context-aware Transformer","date":"2022-08-10","arxiv_id":"2208.05114","n_code_links":3,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["megvii-research/hdr-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/scene-text-recognition-with-permuted","slug":"scene-text-recognition-with-permuted","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","date":"2022-07-14","arxiv_id":"2207.06966","n_code_links":2,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","official":{"repos":["baudm/parseq"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/convolutional-bypasses-are-better-vision","slug":"convolutional-bypasses-are-better-vision","title":"Convolutional Bypasses Are Better Vision Transformer Adapters","date":"2022-07-14","arxiv_id":"2207.07039","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jieshibo/petl-vit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/next-vit-next-generation-vision-transformer","slug":"next-vit-next-generation-vision-transformer","title":"Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios","date":"2022-07-12","arxiv_id":"2207.05501","n_code_links":5,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bytedance/next-vit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/wave-vit-unifying-wavelet-and-transformers","slug":"wave-vit-unifying-wavelet-and-transformers","title":"Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning","date":"2022-07-11","arxiv_id":"2207.04978","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yehli/imagenetmodel"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/improving-the-generalization-of-supervised","slug":"improving-the-generalization-of-supervised","title":"No Reason for No Supervision: Improved Generalization in Supervised Models","date":"2022-06-30","arxiv_id":"2206.15369","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":6,"n_instrument":1,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/vicinity-vision-transformer","slug":"vicinity-vision-transformer","title":"Vicinity Vision Transformer","date":"2022-06-21","arxiv_id":"2206.10552","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opennlplab/vicinity-vision-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/global-context-vision-transformers","slug":"global-context-vision-transformers","title":"Global Context Vision Transformers","date":"2022-06-20","arxiv_id":"2206.09959","n_code_links":8,"syntology":{"ran":21,"of":36,"n_ran_checked":17,"n_instrument":4,"unverified":15,"pointer_only":15,"phrase":"21 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 15 unverified","official":{"repos":["nvlabs/gcvit"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/patch-level-representation-learning-for-self-1","slug":"patch-level-representation-learning-for-self-1","title":"Patch-level Representation Learning for Self-supervised Vision Transformers","date":"2022-06-16","arxiv_id":"2206.07990","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["alinlab/selfpatch"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/omnimae-single-model-masked-pretraining-on","slug":"omnimae-single-model-masked-pretraining-on","title":"OmniMAE: Single Model Masked Pretraining on Images and Videos","date":"2022-06-16","arxiv_id":"2206.08356","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/omnivore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rethinking-generalization-in-few-shot-1","slug":"rethinking-generalization-in-few-shot-1","title":"Rethinking Generalization in Few-Shot Classification","date":"2022-06-15","arxiv_id":"2206.07267","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mrkshllr/FewTURE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-makes-domain-generalization-hard","slug":"what-makes-domain-generalization-hard","title":"Improving generalization by mimicking the human visual diet","date":"2022-06-15","arxiv_id":"2206.07802","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["spandan-madan/human_visual_diet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/neural-prompt-search","slug":"neural-prompt-search","title":"Neural Prompt Search","date":"2022-06-09","arxiv_id":"2206.04673","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":5,"n_instrument":3,"unverified":1,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ZhangYuanhan-AI/NOAH"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mask-dino-towards-a-unified-transformer-based-1","slug":"mask-dino-towards-a-unified-transformer-based-1","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","date":"2022-06-06","arxiv_id":"2206.02777","n_code_links":10,"syntology":{"ran":11,"of":13,"n_ran_checked":3,"n_instrument":8,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","official":{"repos":["idea-research/maskdino"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/decomposing-nerf-for-editing-via-feature","slug":"decomposing-nerf-for-editing-via-feature","title":"Decomposing NeRF for Editing via Feature Field Distillation","date":"2022-05-31","arxiv_id":"2205.15585","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/surface-analysis-with-vision-transformers","slug":"surface-analysis-with-vision-transformers","title":"Surface Analysis with Vision Transformers","date":"2022-05-31","arxiv_id":"2205.15836","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["metrics-lab/surface-vision-transformers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/momentum-stiefel-optimizer-with-applications","slug":"momentum-stiefel-optimizer-with-applications","title":"Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport","date":"2022-05-27","arxiv_id":"2205.14173","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["konglk1203/variationalstiefeloptimizer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-transformers-in-2022-an-update-on-tiny","slug":"vision-transformers-in-2022-an-update-on-tiny","title":"Vision Transformers in 2022: An Update on Tiny ImageNet","date":"2022-05-21","arxiv_id":"2205.10660","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ehuynh1106/TinyImageNet-Transformers"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-to-count-anything-reference-less","slug":"learning-to-count-anything-reference-less","title":"Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision","date":"2022-05-20","arxiv_id":"2205.10203","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["activevisionlab/learningtocountanything"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-graph-transformer-for-whole-slide-image","slug":"a-graph-transformer-for-whole-slide-image","title":"A graph-transformer for whole slide image classification","date":"2022-05-19","arxiv_id":"2205.09671","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vkola-lab/tmi2022"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/aggpose-deep-aggregation-vision-transformer","slug":"aggpose-deep-aggregation-vision-transformer","title":"AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation","date":"2022-05-11","arxiv_id":"2205.05277","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","official":{"repos":["szar-lab/aggpose"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/sequencer-deep-lstm-for-image-classification","slug":"sequencer-deep-lstm-for-image-classification","title":"Sequencer: Deep LSTM for Image Classification","date":"2022-05-04","arxiv_id":"2205.01972","n_code_links":5,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["okojoalg/sequencer","rwightman/pytorch-image-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/better-plain-vit-baselines-for-imagenet-1k","slug":"better-plain-vit-baselines-for-imagenet-1k","title":"Better plain ViT baselines for ImageNet-1k","date":"2022-05-03","arxiv_id":"2205.01580","n_code_links":7,"syntology":{"ran":23,"of":24,"n_ran_checked":20,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/big_vision"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/vitpose-simple-vision-transformer-baselines","slug":"vitpose-simple-vision-transformer-baselines","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","date":"2022-04-26","arxiv_id":"2204.12484","n_code_links":6,"syntology":{"ran":18,"of":31,"n_ran_checked":12,"n_instrument":6,"unverified":13,"pointer_only":6,"phrase":"18 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 13 unverified","official":{"repos":["vitae-transformer/vitpose"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/relvit-concept-guided-vision-transformer-for-1","slug":"relvit-concept-guided-vision-transformer-for-1","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","date":"2022-04-24","arxiv_id":"2204.11167","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":3,"n_instrument":3,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["NVlabs/RelViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/not-all-tokens-are-equal-human-centric-visual","slug":"not-all-tokens-are-equal-human-centric-visual","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","date":"2022-04-19","arxiv_id":"2204.08680","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zengwang430521/tcformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/temporally-efficient-vision-transformer-for","slug":"temporally-efficient-vision-transformer-for","title":"Temporally Efficient Vision Transformer for Video Instance Segmentation","date":"2022-04-18","arxiv_id":"2204.08412","n_code_links":3,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hustvl/tevit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/safe-self-refinement-for-transformer-based","slug":"safe-self-refinement-for-transformer-based","title":"Safe Self-Refinement for Transformer-based Domain Adaptation","date":"2022-04-16","arxiv_id":"2204.07683","n_code_links":1,"syntology":{"ran":9,"of":19,"n_ran_checked":3,"n_instrument":6,"unverified":10,"pointer_only":1,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified","official":{"repos":["tsun/ssrt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":10,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/pushing-the-limits-of-simple-pipelines-for","slug":"pushing-the-limits-of-simple-pipelines-for","title":"Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference","date":"2022-04-15","arxiv_id":"2204.07305","n_code_links":1,"syntology":{"ran":14,"of":19,"n_ran_checked":8,"n_instrument":6,"unverified":5,"pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hushell/pmf_cvpr22"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/davit-dual-attention-vision-transformers","slug":"davit-dual-attention-vision-transformers","title":"DaViT: Dual Attention Vision Transformers","date":"2022-04-07","arxiv_id":"2204.03645","n_code_links":4,"syntology":{"ran":8,"of":15,"n_ran_checked":6,"n_instrument":2,"unverified":7,"pointer_only":0,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","official":{"repos":["dingmyu/davit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/improving-vision-transformers-by-revisiting","slug":"improving-vision-transformers-by-revisiting","title":"Improving Vision Transformers by Revisiting High-frequency Components","date":"2022-04-03","arxiv_id":"2204.00993","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":9,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jiawangbai/HAT"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploring-plain-vision-transformer-backbones","slug":"exploring-plain-vision-transformer-backbones","title":"Exploring Plain Vision Transformer Backbones for Object Detection","date":"2022-03-30","arxiv_id":"2203.16527","n_code_links":11,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/detectron2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/affine-medical-image-registration-with-coarse","slug":"affine-medical-image-registration-with-coarse","title":"Affine Medical Image Registration with Coarse-to-Fine Vision Transformer","date":"2022-03-29","arxiv_id":"2203.15216","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cwmok/C2FViT"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/fine-tuning-image-transformers-using","slug":"fine-tuning-image-transformers-using","title":"Fine-tuning Image Transformers using Learnable Memory","date":"2022-03-29","arxiv_id":"2203.15243","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/sepvit-separable-vision-transformer","slug":"sepvit-separable-vision-transformer","title":"SepViT: Separable Vision Transformer","date":"2022-03-29","arxiv_id":"2203.15380","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["liwei109/sepvit"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/training-free-transformer-architecture-search","slug":"training-free-transformer-architecture-search","title":"Training-free Transformer Architecture Search","date":"2022-03-23","arxiv_id":"2203.12217","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/unsupervised-salient-object-detection-with","slug":"unsupervised-salient-object-detection-with","title":"Unsupervised Salient Object Detection with Spectral Cluster Voting","date":"2022-03-23","arxiv_id":"2203.12614","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":2,"n_instrument":3,"unverified":4,"pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["noelshin/selfmask"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/focal-modulation-networks","slug":"focal-modulation-networks","title":"Focal Modulation Networks","date":"2022-03-22","arxiv_id":"2203.11926","n_code_links":9,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/FocalNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-patch-to-cluster-attention-in-vision","slug":"learning-patch-to-cluster-attention-in-vision","title":"PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers","date":"2022-03-22","arxiv_id":"2203.11987","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ivmcl/pacavit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/scalablevit-rethinking-the-context-oriented","slug":"scalablevit-rethinking-the-context-oriented","title":"ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer","date":"2022-03-21","arxiv_id":"2203.10790","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yangr116/scalablevit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/hyperbolic-vision-transformers-combining","slug":"hyperbolic-vision-transformers-combining","title":"Hyperbolic Vision Transformers: Combining Improvements in Metric Learning","date":"2022-03-21","arxiv_id":"2203.10833","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["htdt/hyp_metric"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/attribute-surrogates-learning-and-spectral","slug":"attribute-surrogates-learning-and-spectral","title":"Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning","date":"2022-03-17","arxiv_id":"2203.09064","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["stomachcold/hctransformers"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/unsupervised-semantic-segmentation-by-2","slug":"unsupervised-semantic-segmentation-by-2","title":"Unsupervised Semantic Segmentation by Distilling Feature Correspondences","date":"2022-03-16","arxiv_id":"2203.08414","n_code_links":3,"syntology":{"ran":11,"of":14,"n_ran_checked":7,"n_instrument":4,"unverified":3,"pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["mhamilton723/STEGO"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/the-devil-is-in-the-details-window-based","slug":"the-devil-is-in-the-details-window-based","title":"The Devil Is in the Details: Window-based Attention for Image Compression","date":"2022-03-16","arxiv_id":"2203.08450","n_code_links":2,"syntology":{"ran":15,"of":15,"n_ran_checked":11,"n_instrument":4,"unverified":0,"pointer_only":11,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["googolxx/stf"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/smoothing-matters-momentum-transformer-for","slug":"smoothing-matters-momentum-transformer-for","title":"Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation","date":"2022-03-15","arxiv_id":"2203.07988","n_code_links":1,"syntology":{"ran":3,"of":8,"n_ran_checked":1,"n_instrument":2,"unverified":5,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["alpc91/transda"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/unified-visual-transformer-compression-1","slug":"unified-visual-transformer-compression-1","title":"Unified Visual Transformer Compression","date":"2022-03-15","arxiv_id":"2203.08243","n_code_links":1,"syntology":{"ran":9,"of":16,"n_ran_checked":6,"n_instrument":3,"unverified":7,"pointer_only":3,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["VITA-Group/UVC"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/coarse-to-fine-vision-transformer","slug":"coarse-to-fine-vision-transformer","title":"CF-ViT: A General Coarse-to-Fine Method for Vision Transformer","date":"2022-03-08","arxiv_id":"2203.03821","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["chenmnz/cf-vit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/edgeformer-improving-light-weight-convnets-by","slug":"edgeformer-improving-light-weight-convnets-by","title":"ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer","date":"2022-03-08","arxiv_id":"2203.03952","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hkzhang91/edgeformer","hkzhang91/pacc-net","hkzhang91/parc-net"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/wavemix-resource-efficient-token-mixing-for","slug":"wavemix-resource-efficient-token-mixing-for","title":"WaveMix: Resource-efficient Token Mixing for Images","date":"2022-03-07","arxiv_id":"2203.03689","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["pranavphoenix/WaveMix"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-class-token-transformer-for-weakly","slug":"multi-class-token-transformer-for-weakly","title":"Multi-class Token Transformer for Weakly Supervised Semantic Segmentation","date":"2022-03-06","arxiv_id":"2203.02891","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["xulianuwa/mctformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/new-crfs-neural-window-fully-connected-crfs-1","slug":"new-crfs-neural-window-fully-connected-crfs-1","title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","date":"2022-03-03","arxiv_id":"2203.01502","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["aliyun/NeWCRFs"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/vitaev2-vision-transformer-advanced-by","slug":"vitaev2-vision-transformer-advanced-by","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","date":"2022-02-21","arxiv_id":"2202.10108","n_code_links":8,"syntology":{"ran":22,"of":25,"n_ran_checked":16,"n_instrument":6,"unverified":3,"pointer_only":4,"phrase":"22 ran (of which 8 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ViTAE-Transformer/ViTAE-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed"]}}},{"paper":"/paper/patches-are-all-you-need-1","slug":"patches-are-all-you-need-1","title":"Patches Are All You Need?","date":"2022-01-24","arxiv_id":"2201.09792","n_code_links":12,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 5 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["locuslab/convmixer","tmp-iclr/convmixer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/q-vit-fully-differentiable-quantization-for","slug":"q-vit-fully-differentiable-quantization-for","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","date":"2022-01-19","arxiv_id":"2201.07703","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhexinli/Q-ViT-DeiT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/swinunet3d-a-hierarchical-architecture-for","slug":"swinunet3d-a-hierarchical-architecture-for","title":"SwinUNet3D -- A Hierarchical Architecture for Deep Traffic Prediction using Shifted Window Transformers","date":"2022-01-17","arxiv_id":"2201.06390","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bojesomo/Traffic4Cast2021-SwinUNet3D"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-transformer-slimming-multi-dimension","slug":"vision-transformer-slimming-multi-dimension","title":"Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space","date":"2022-01-03","arxiv_id":"2201.00814","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["arnav0400/vit-slim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/splicing-vit-features-for-semantic-appearance","slug":"splicing-vit-features-for-semantic-appearance","title":"Splicing ViT Features for Semantic Appearance Transfer","date":"2022-01-02","arxiv_id":"2201.00424","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["omerbt/Splice"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/pale-transformer-a-general-vision-transformer","slug":"pale-transformer-a-general-vision-transformer","title":"Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention","date":"2021-12-28","arxiv_id":"2112.14000","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["BR-IDL/PaddleViT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/vision-transformer-for-small-size-datasets","slug":"vision-transformer-for-small-size-datasets","title":"Vision Transformer for Small-Size Datasets","date":"2021-12-27","arxiv_id":"2112.13492","n_code_links":5,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aanna0701/SPT_LSA_ViT"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/spvit-enabling-faster-vision-transformers-via","slug":"spvit-enabling-faster-vision-transformers-via","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","date":"2021-12-27","arxiv_id":"2112.13890","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["peiyanflying/spvit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/learned-queries-for-efficient-local-attention","slug":"learned-queries-for-efficient-local-attention","title":"Learned Queries for Efficient Local Attention","date":"2021-12-21","arxiv_id":"2112.11435","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["moabarar/qna"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/adavit-adaptive-tokens-for-efficient-vision","slug":"adavit-adaptive-tokens-for-efficient-vision","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","date":"2021-12-14","arxiv_id":"2112.07658","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/deep-vit-features-as-dense-visual-descriptors","slug":"deep-vit-features-as-dense-visual-descriptors","title":"Deep ViT Features as Dense Visual Descriptors","date":"2021-12-10","arxiv_id":"2112.05814","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/injecting-semantic-concepts-into-end-to-end","slug":"injecting-semantic-concepts-into-end-to-end","title":"Injecting Semantic Concepts into End-to-End Image Captioning","date":"2021-12-09","arxiv_id":"2112.05230","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jacobswan1/ViTCAP"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ats-adaptive-token-sampling-for-efficient","slug":"ats-adaptive-token-sampling-for-efficient","title":"Adaptive Token Sampling For Efficient Vision Transformers","date":"2021-11-30","arxiv_id":"2111.15667","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["adaptivetokensampling/ATS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/pixelated-butterfly-simple-and-efficient-1","slug":"pixelated-butterfly-simple-and-efficient-1","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","date":"2021-11-30","arxiv_id":"2112.00029","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["HazyResearch/pixelfly"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/fq-vit-fully-quantized-vision-transformer","slug":"fq-vit-fully-quantized-vision-transformer","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","date":"2021-11-27","arxiv_id":"2111.13824","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["megvii-research/FQ-ViT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/scene-representation-transformer-geometry","slug":"scene-representation-transformer-geometry","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","date":"2021-11-25","arxiv_id":"2111.13152","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/pruning-self-attentions-into-convolutional","slug":"pruning-self-attentions-into-convolutional","title":"Pruning Self-attentions into Convolutional Layers in Single Path","date":"2021-11-23","arxiv_id":"2111.11802","n_code_links":3,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhuang-group/spvit","zip-group/spvit","ziplab/spvit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-supervised-pre-training-for-transformer","slug":"self-supervised-pre-training-for-transformer","title":"Self-Supervised Pre-Training for Transformer-Based Person Re-Identification","date":"2021-11-23","arxiv_id":"2111.12084","n_code_links":3,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["michuanhaohao/transreid-ssl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/transmorph-transformer-for-unsupervised","slug":"transmorph-transformer-for-unsupervised","title":"TransMorph: Transformer for unsupervised medical image registration","date":"2021-11-19","arxiv_id":"2111.10480","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["junyuchen245/TransMorph_Transformer_for_Medical_Image_Registration"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/fastflow-unsupervised-anomaly-detection-and","slug":"fastflow-unsupervised-anomaly-detection-and","title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows","date":"2021-11-15","arxiv_id":"2111.07677","n_code_links":5,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/generalized-radiograph-representation","slug":"generalized-radiograph-representation","title":"Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports","date":"2021-11-04","arxiv_id":"2111.03452","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["funnyzhou/refers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mvt-multi-view-vision-transformer-for-3d","slug":"mvt-multi-view-vision-transformer-for-3d","title":"MVT: Multi-view Vision Transformer for 3D Object Recognition","date":"2021-10-25","arxiv_id":"2110.13083","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shanshuo/MVT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/history-aware-multimodal-transformer-for","slug":"history-aware-multimodal-transformer-for","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","date":"2021-10-25","arxiv_id":"2110.13309","n_code_links":1,"syntology":{"ran":7,"of":15,"n_ran_checked":7,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":"/paper/ssast-self-supervised-audio-spectrogram","slug":"ssast-self-supervised-audio-spectrogram","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","date":"2021-10-19","arxiv_id":"2110.09784","n_code_links":3,"syntology":{"ran":13,"of":16,"n_ran_checked":13,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["YuanGongND/ssast"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/hrformer-high-resolution-transformer-for","slug":"hrformer-high-resolution-transformer-for","title":"HRFormer: High-Resolution Transformer for Dense Prediction","date":"2021-10-18","arxiv_id":"2110.09408","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","official":{"repos":["HRNet/HRFormer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/memo-test-time-robustness-via-adaptation-and","slug":"memo-test-time-robustness-via-adaptation-and","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","date":"2021-10-18","arxiv_id":"2110.09506","n_code_links":2,"syntology":{"ran":14,"of":18,"n_ran_checked":3,"n_instrument":11,"unverified":4,"pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 11 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zhangmarvin/memo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"paper":"/paper/certified-patch-robustness-via-smoothed-1","slug":"certified-patch-robustness-via-smoothed-1","title":"Certified Patch Robustness via Smoothed Vision Transformers","date":"2021-10-11","arxiv_id":"2110.07719","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["madrylab/smoothed-vit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/nvit-vision-transformer-compression-and-1","slug":"nvit-vision-transformer-compression-and-1","title":"Global Vision Transformer Pruning with Hessian-Aware Saliency","date":"2021-10-10","arxiv_id":"2110.04869","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/mobilevit-light-weight-general-purpose-and","slug":"mobilevit-light-weight-general-purpose-and","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","date":"2021-10-05","arxiv_id":"2110.02178","n_code_links":31,"syntology":{"ran":53,"of":68,"n_ran_checked":44,"n_instrument":9,"unverified":15,"pointer_only":18,"phrase":"53 ran (of which 31 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 9 where Syntology's instrument failed) · 15 unverified","official":{"repos":["apple/ml-cvnets"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/learning-to-predict-trustworthiness-with","slug":"learning-to-predict-trustworthiness-with","title":"Learning to Predict Trustworthiness with Steep Slope Loss","date":"2021-09-30","arxiv_id":"2110.00054","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["luoyan407/predict_trustworthiness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cctrans-simplifying-and-improving-crowd","slug":"cctrans-simplifying-and-improving-crowd","title":"CCTrans: Simplifying and Improving Crowd Counting with Transformer","date":"2021-09-29","arxiv_id":"2109.14483","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/pass-an-imagenet-replacement-for-self","slug":"pass-an-imagenet-replacement-for-self","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","date":"2021-09-27","arxiv_id":"2109.13228","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":10,"n_instrument":1,"unverified":3,"pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["yukimasano/PASS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/improving-360-monocular-depth-estimation-via","slug":"improving-360-monocular-depth-estimation-via","title":"Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning","date":"2021-09-22","arxiv_id":"2109.10563","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/efficient-hybrid-transformer-learning-global","slug":"efficient-hybrid-transformer-learning-global","title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","date":"2021-09-18","arxiv_id":"2109.08937","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["WangLibo1995/GeoSeg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-transformer-for-single-image-super","slug":"efficient-transformer-for-single-image-super","title":"Transformer for Single Image Super-Resolution","date":"2021-08-25","arxiv_id":"2108.11084","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":7,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["luissen/esrt"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/causal-attention-for-unbiased-visual","slug":"causal-attention-for-unbiased-visual","title":"Causal Attention for Unbiased Visual Recognition","date":"2021-08-19","arxiv_id":"2108.08782","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["wangt-cn/caam"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/tvt-transferable-vision-transformer-for","slug":"tvt-transferable-vision-transformer-for","title":"TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation","date":"2021-08-12","arxiv_id":"2108.05988","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["uta-smile/TVT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/token-shift-transformer-for-video","slug":"token-shift-transformer-for-video","title":"Token Shift Transformer for Video Classification","date":"2021-08-05","arxiv_id":"2108.02432","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["VideoNetworks/TokShift-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/vision-transformer-with-progressive-sampling","slug":"vision-transformer-with-progressive-sampling","title":"Vision Transformer with Progressive Sampling","date":"2021-08-03","arxiv_id":"2108.01684","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yuexy/PS-ViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/glit-neural-architecture-search-for-global","slug":"glit-neural-architecture-search-for-global","title":"GLiT: Neural Architecture Search for Global and Local Image Transformer","date":"2021-07-07","arxiv_id":"2107.02960","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["bychen515/glit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/focal-self-attention-for-local-global","slug":"focal-self-attention-for-local-global","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","date":"2021-07-01","arxiv_id":"2107.00641","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/Focal-Transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/scaling-vision-with-sparse-mixture-of-experts","slug":"scaling-vision-with-sparse-mixture-of-experts","title":"Scaling Vision with Sparse Mixture of Experts","date":"2021-06-10","arxiv_id":"2106.05974","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/vmoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/grounding-inductive-biases-in-natural-images","slug":"grounding-inductive-biases-in-natural-images","title":"Grounding inductive biases in natural images:invariance stems from variations in data","date":"2021-06-09","arxiv_id":"2106.05121","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/grounding-inductive-biases"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/demystifying-local-vision-transformer-sparse","slug":"demystifying-local-vision-transformer-sparse","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","date":"2021-06-08","arxiv_id":"2106.04263","n_code_links":1,"syntology":{"ran":11,"of":16,"n_ran_checked":11,"n_instrument":0,"unverified":5,"pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["atten4vis/demystifylocalvit"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/vitae-vision-transformer-advanced-by","slug":"vitae-vision-transformer-advanced-by","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","date":"2021-06-07","arxiv_id":"2106.03348","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Annbless/ViTAE"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/person-re-identification-with-a-locally-aware","slug":"person-re-identification-with-a-locally-aware","title":"Person Re-Identification with a Locally Aware Transformer","date":"2021-06-07","arxiv_id":"2106.03720","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["SiddhantKapil/LA-Transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"fc5263da5c65f380ea6f834fc8efbd8a305d8b4a298175547b422225cc700aef","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}