{"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":"/dataset/imagenet/papers/4","list_of":"/dataset/imagenet","dataset":"ImageNet","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"order":"archive","order_definition":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":4,"pages_in_order":7,"rows_per_page":100,"rows":[301,400],"of":630,"counts":{"papers_with_a_benchmark_row":630,"with_a_code_link":588,"where_syntology_ran_a_sample":361,"not_listed_spam_title":0,"listed":630,"listed_where_code_ran":361,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":312,"every_run_a_failure_of_syntologys_instrument":49,"listed_with_a_run_with_no_instrument_failure":312,"listed_every_run_a_failure_of_syntologys_instrument":49,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/dataset/imagenet","prev":"/dataset/imagenet/papers/3","next":"/dataset/imagenet/papers/5","papers":[{"paper":"/paper/idarts-improving-darts-by-node-normalization","slug":"idarts-improving-darts-by-node-normalization","title":"iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization","date":"2021-08-25","arxiv_id":"2108.11014","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/contextual-convolutional-neural-networks","slug":"contextual-convolutional-neural-networks","title":"Contextual Convolutional Neural Networks","date":"2021-08-17","arxiv_id":"2108.07387","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/eeea-net-an-early-exit-evolutionary-neural","slug":"eeea-net-an-early-exit-evolutionary-neural","title":"EEEA-Net: An Early Exit Evolutionary Neural Architecture Search","date":"2021-08-13","arxiv_id":"2108.06156","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/evo-vit-slow-fast-token-evolution-for-dynamic","slug":"evo-vit-slow-fast-token-evolution-for-dynamic","title":"Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer","date":"2021-08-03","arxiv_id":"2108.01390","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["YifanXu74/Evo-ViT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/evo-vit-slow-fast-token-evolution-for-dynamic#ran","syntology_url":"https://syntology.ai/paper/2108.01390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.01390"}}}},{"paper":"/paper/group-fisher-pruning-for-practical-network","slug":"group-fisher-pruning-for-practical-network","title":"Group Fisher Pruning for Practical Network Compression","date":"2021-08-02","arxiv_id":"2108.00708","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/hierarchical-self-supervised-augmented","slug":"hierarchical-self-supervised-augmented","title":"Hierarchical Self-supervised Augmented Knowledge Distillation","date":"2021-07-29","arxiv_id":"2107.13715","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["winycg/HSAKD"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hierarchical-self-supervised-augmented#ran","syntology_url":"https://syntology.ai/paper/2107.13715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.13715"}}}},{"paper":"/paper/rethinking-and-improving-relative-position","slug":"rethinking-and-improving-relative-position","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","date":"2021-07-29","arxiv_id":"2107.14222","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":7,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["microsoft/cream"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rethinking-and-improving-relative-position#ran","syntology_url":"https://syntology.ai/paper/2107.14222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.14222"}}}},{"paper":"/paper/contextual-transformer-networks-for-visual","slug":"contextual-transformer-networks-for-visual","title":"Contextual Transformer Networks for Visual Recognition","date":"2021-07-26","arxiv_id":"2107.12292","rows_on_this_dataset":3,"code_links":7,"syntology":null},{"paper":"/paper/parametric-contrastive-learning","slug":"parametric-contrastive-learning","title":"Parametric Contrastive Learning","date":"2021-07-26","arxiv_id":"2107.12028","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["dvlab-research/parametric-contrastive-learning","jiequancui/Parametric-Contrastive-Learning"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/parametric-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2107.12028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12028"}}}},{"paper":"/paper/go-wider-instead-of-deeper","slug":"go-wider-instead-of-deeper","title":"Go Wider Instead of Deeper","date":"2021-07-25","arxiv_id":"2107.11817","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/m-darts-model-uncertainty-aware","slug":"m-darts-model-uncertainty-aware","title":"$μ$DARTS: Model Uncertainty-Aware Differentiable Architecture Search","date":"2021-07-24","arxiv_id":"2107.11500","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bias-loss-for-mobile-neural-networks","slug":"bias-loss-for-mobile-neural-networks","title":"Bias Loss for Mobile Neural Networks","date":"2021-07-23","arxiv_id":"2107.11170","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/cyclemlp-a-mlp-like-architecture-for-dense","slug":"cyclemlp-a-mlp-like-architecture-for-dense","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","date":"2021-07-21","arxiv_id":"2107.10224","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":2,"official":{"repos":["ShoufaChen/CycleMLP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cyclemlp-a-mlp-like-architecture-for-dense#ran","syntology_url":"https://syntology.ai/paper/2107.10224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.10224"}}}},{"paper":"/paper/ressl-relational-self-supervised-learning","slug":"ressl-relational-self-supervised-learning","title":"ReSSL: Relational Self-Supervised Learning with Weak Augmentation","date":"2021-07-20","arxiv_id":"2107.09282","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["KyleZheng1997/ReSSL"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ressl-relational-self-supervised-learning#ran","syntology_url":"https://syntology.ai/paper/2107.09282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09282"}}}},{"paper":"/paper/visual-parser-representing-part-whole","slug":"visual-parser-representing-part-whole","title":"Visual Parser: Representing Part-whole Hierarchies with Transformers","date":"2021-07-13","arxiv_id":"2107.05790","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/collaboration-of-experts-achieving-80-top-1","slug":"collaboration-of-experts-achieving-80-top-1","title":"Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs","date":"2021-07-08","arxiv_id":"2107.03815","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"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","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/glit-neural-architecture-search-for-global#ran","syntology_url":"https://syntology.ai/paper/2107.02960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02960"}}}},{"paper":"/paper/autoformer-searching-transformers-for-visual","slug":"autoformer-searching-transformers-for-visual","title":"AutoFormer: Searching Transformers for Visual Recognition","date":"2021-07-01","arxiv_id":"2107.00651","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/cswin-transformer-a-general-vision","slug":"cswin-transformer-a-general-vision","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","date":"2021-07-01","arxiv_id":"2107.00652","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["microsoft/CSWin-Transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cswin-transformer-a-general-vision#ran","syntology_url":"https://syntology.ai/paper/2107.00652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00652"}}}},{"paper":"/paper/global-filter-networks-for-image","slug":"global-filter-networks-for-image","title":"Global Filter Networks for Image Classification","date":"2021-07-01","arxiv_id":"2107.00645","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":4,"pointer_only_for_licence":5,"official":{"repos":["raoyongming/GFNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/global-filter-networks-for-image#ran","syntology_url":"https://syntology.ai/paper/2107.00645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00645"}}}},{"paper":"/paper/pvtv2-improved-baselines-with-pyramid-vision","slug":"pvtv2-improved-baselines-with-pyramid-vision","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","date":"2021-06-25","arxiv_id":"2106.13797","rows_on_this_dataset":5,"code_links":18,"syntology":null},{"paper":"/paper/volo-vision-outlooker-for-visual-recognition","slug":"volo-vision-outlooker-for-visual-recognition","title":"VOLO: Vision Outlooker for Visual Recognition","date":"2021-06-24","arxiv_id":"2106.13112","rows_on_this_dataset":7,"code_links":7,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["rwightman/pytorch-image-models","sail-sg/volo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/volo-vision-outlooker-for-visual-recognition#ran","syntology_url":"https://syntology.ai/paper/2106.13112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13112"}}}},{"paper":"/paper/ac-dc-alternating-compressed-decompressed","slug":"ac-dc-alternating-compressed-decompressed","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","date":"2021-06-23","arxiv_id":"2106.12379","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["IST-DASLab/ACDC"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ac-dc-alternating-compressed-decompressed#ran","syntology_url":"https://syntology.ai/paper/2106.12379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12379"}}}},{"paper":"/paper/tokenlearner-what-can-8-learned-tokens-do-for","slug":"tokenlearner-what-can-8-learned-tokens-do-for","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","date":"2021-06-21","arxiv_id":"2106.11297","rows_on_this_dataset":2,"code_links":11,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["google-research/scenic"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tokenlearner-what-can-8-learned-tokens-do-for#ran","syntology_url":"https://syntology.ai/paper/2106.11297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11297"}}}},{"paper":"/paper/sparse-training-via-boosting-pruning","slug":"sparse-training-via-boosting-pruning","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","date":"2021-06-19","arxiv_id":"2106.10404","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["Shiweiliuiiiiiii/GraNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sparse-training-via-boosting-pruning#ran","syntology_url":"https://syntology.ai/paper/2106.10404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10404"}}}},{"paper":"/paper/efficient-self-supervised-vision-transformers","slug":"efficient-self-supervised-vision-transformers","title":"Efficient Self-supervised Vision Transformers for Representation Learning","date":"2021-06-17","arxiv_id":"2106.09785","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["microsoft/esvit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-self-supervised-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.09785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09785"}}}},{"paper":"/paper/xcit-cross-covariance-image-transformers","slug":"xcit-cross-covariance-image-transformers","title":"XCiT: Cross-Covariance Image Transformers","date":"2021-06-17","arxiv_id":"2106.09681","rows_on_this_dataset":4,"code_links":12,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":11,"official":{"repos":["facebookresearch/xcit","rwightman/pytorch-image-models"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xcit-cross-covariance-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.09681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09681"}}}},{"paper":"/paper/how-does-topology-of-neural-architectures","slug":"how-does-topology-of-neural-architectures","title":"How does topology of neural architectures impact gradient propagation and model performance?","date":"2021-06-16","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/beit-bert-pre-training-of-image-transformers","slug":"beit-bert-pre-training-of-image-transformers","title":"BEiT: BERT Pre-Training of Image Transformers","date":"2021-06-15","arxiv_id":"2106.08254","rows_on_this_dataset":4,"code_links":14,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":6,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/beit-bert-pre-training-of-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.08254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08254"}}}},{"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","rows_on_this_dataset":17,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-vision-with-sparse-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2106.05974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05974"}}}},{"paper":"/paper/coatnet-marrying-convolution-and-attention","slug":"coatnet-marrying-convolution-and-attention","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","date":"2021-06-09","arxiv_id":"2106.04803","rows_on_this_dataset":7,"code_links":14,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coatnet-marrying-convolution-and-attention#ran","syntology_url":"https://syntology.ai/paper/2106.04803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04803"}}}},{"paper":"/paper/knowledge-distillation-a-good-teacher-is","slug":"knowledge-distillation-a-good-teacher-is","title":"Knowledge distillation: A good teacher is patient and consistent","date":"2021-06-09","arxiv_id":"2106.05237","rows_on_this_dataset":1,"code_links":10,"syntology":null},{"paper":"/paper/scaling-vision-transformers","slug":"scaling-vision-transformers","title":"Scaling Vision Transformers","date":"2021-06-08","arxiv_id":"2106.04560","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/refiner-refining-self-attention-for-vision","slug":"refiner-refining-self-attention-for-vision","title":"Refiner: Refining Self-attention for Vision Transformers","date":"2021-06-07","arxiv_id":"2106.03714","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["zhoudaquan/Refiner_ViT"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/refiner-refining-self-attention-for-vision#ran","syntology_url":"https://syntology.ai/paper/2106.03714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03714"}}}},{"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","rows_on_this_dataset":6,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vitae-vision-transformer-advanced-by#ran","syntology_url":"https://syntology.ai/paper/2106.03348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03348"}}}},{"paper":"/paper/x-volution-on-the-unification-of-convolution","slug":"x-volution-on-the-unification-of-convolution","title":"X-volution: On the unification of convolution and self-attention","date":"2021-06-04","arxiv_id":"2106.02253","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/dynamicvit-efficient-vision-transformers-with","slug":"dynamicvit-efficient-vision-transformers-with","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","date":"2021-06-03","arxiv_id":"2106.02034","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["raoyongming/DynamicViT"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dynamicvit-efficient-vision-transformers-with#ran","syntology_url":"https://syntology.ai/paper/2106.02034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02034"}}}},{"paper":"/paper/when-vision-transformers-outperform-resnets","slug":"when-vision-transformers-outperform-resnets","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","date":"2021-06-03","arxiv_id":"2106.01548","rows_on_this_dataset":6,"code_links":2,"syntology":null},{"paper":"/paper/container-context-aggregation-network","slug":"container-context-aggregation-network","title":"Container: Context Aggregation Network","date":"2021-06-02","arxiv_id":"2106.01401","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["allenai/container","gaopengcuhk/Container"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/container-context-aggregation-network#ran","syntology_url":"https://syntology.ai/paper/2106.01401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01401"}}}},{"paper":"/paper/not-all-images-are-worth-16x16-words-dynamic","slug":"not-all-images-are-worth-16x16-words-dynamic","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","date":"2021-05-31","arxiv_id":"2105.15075","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["blackfeather-wang/Dynamic-Vision-Transformer","blackfeather-wang/dynamic-vision-transformer-mindspore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/not-all-images-are-worth-16x16-words-dynamic#ran","syntology_url":"https://syntology.ai/paper/2105.15075","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.15075"}}}},{"paper":"/paper/rest-an-efficient-transformer-for-visual","slug":"rest-an-efficient-transformer-for-visual","title":"ResT: An Efficient Transformer for Visual Recognition","date":"2021-05-28","arxiv_id":"2105.13677","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":9,"official":{"repos":["wofmanaf/ResT"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rest-an-efficient-transformer-for-visual#ran","syntology_url":"https://syntology.ai/paper/2105.13677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13677"}}}},{"paper":"/paper/drawing-multiple-augmentation-samples-per","slug":"drawing-multiple-augmentation-samples-per","title":"Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error","date":"2021-05-27","arxiv_id":"2105.13343","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/aggregating-nested-transformers","slug":"aggregating-nested-transformers","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","date":"2021-05-26","arxiv_id":"2105.12723","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":26,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":18,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":6,"official":{"repos":["google-research/nested-transformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/aggregating-nested-transformers#ran","syntology_url":"https://syntology.ai/paper/2105.12723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12723"}}}},{"paper":"/paper/unsupervised-visual-representation-learning-3","slug":"unsupervised-visual-representation-learning-3","title":"Unsupervised Visual Representation Learning by Online Constrained K-Means","date":"2021-05-24","arxiv_id":"2105.11527","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["idstcv/coke"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-visual-representation-learning-3#ran","syntology_url":"https://syntology.ai/paper/2105.11527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11527"}}}},{"paper":"/paper/correlated-input-dependent-label-noise-in","slug":"correlated-input-dependent-label-noise-in","title":"Correlated Input-Dependent Label Noise in Large-Scale Image Classification","date":"2021-05-19","arxiv_id":"2105.10305","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/divide-and-contrast-self-supervised-learning","slug":"divide-and-contrast-self-supervised-learning","title":"Divide and Contrast: Self-supervised Learning from Uncurated Data","date":"2021-05-17","arxiv_id":"2105.08054","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pay-attention-to-mlps","slug":"pay-attention-to-mlps","title":"Pay Attention to MLPs","date":"2021-05-17","arxiv_id":"2105.08050","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":44,"samples_ran":34,"samples_constructed":15,"samples_ran_checked":31,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":11,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pay-attention-to-mlps#ran","syntology_url":"https://syntology.ai/paper/2105.08050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08050"}}}},{"paper":"/paper/rethinking-the-design-principles-of-robust","slug":"rethinking-the-design-principles-of-robust","title":"Towards Robust Vision Transformer","date":"2021-05-17","arxiv_id":"2105.07926","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/vicreg-variance-invariance-covariance","slug":"vicreg-variance-invariance-covariance","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","date":"2021-05-11","arxiv_id":"2105.04906","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":17,"samples_ran":15,"samples_constructed":3,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["facebookresearch/vicreg"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vicreg-variance-invariance-covariance#ran","syntology_url":"https://syntology.ai/paper/2105.04906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.04906"}}}},{"paper":"/paper/self-supervised-learning-with-swin","slug":"self-supervised-learning-with-swin","title":"Self-Supervised Learning with Swin Transformers","date":"2021-05-10","arxiv_id":"2105.04553","rows_on_this_dataset":2,"code_links":6,"syntology":null},{"paper":"/paper/conformer-local-features-coupling-global","slug":"conformer-local-features-coupling-global","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","date":"2021-05-09","arxiv_id":"2105.03889","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":7,"samples_constructed":5,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["pengzhiliang/Conformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/conformer-local-features-coupling-global#ran","syntology_url":"https://syntology.ai/paper/2105.03889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03889"}}}},{"paper":"/paper/basisnet-two-stage-model-synthesis-for-1","slug":"basisnet-two-stage-model-synthesis-for-1","title":"BasisNet: Two-stage Model Synthesis for Efficient Inference","date":"2021-05-07","arxiv_id":"2105.03014","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/network-pruning-that-matters-a-case-study-on-1","slug":"network-pruning-that-matters-a-case-study-on-1","title":"Network Pruning That Matters: A Case Study on Retraining Variants","date":"2021-05-07","arxiv_id":"2105.03193","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":2,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["lehduong/NPTM"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/network-pruning-that-matters-a-case-study-on-1#ran","syntology_url":"https://syntology.ai/paper/2105.03193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03193"}}}},{"paper":"/paper/resmlp-feedforward-networks-for-image","slug":"resmlp-feedforward-networks-for-image","title":"ResMLP: Feedforward networks for image classification with data-efficient training","date":"2021-05-07","arxiv_id":"2105.03404","rows_on_this_dataset":12,"code_links":19,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["facebookresearch/deit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/resmlp-feedforward-networks-for-image#ran","syntology_url":"https://syntology.ai/paper/2105.03404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03404"}}}},{"paper":"/paper/do-you-even-need-attention-a-stack-of-feed","slug":"do-you-even-need-attention-a-stack-of-feed","title":"Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet","date":"2021-05-06","arxiv_id":"2105.02723","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/beyond-self-attention-external-attention","slug":"beyond-self-attention-external-attention","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","date":"2021-05-05","arxiv_id":"2105.02358","rows_on_this_dataset":1,"code_links":7,"syntology":null},{"paper":"/paper/repmlp-re-parameterizing-convolutions-into","slug":"repmlp-re-parameterizing-convolutions-into","title":"RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition","date":"2021-05-05","arxiv_id":"2105.01883","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["DingXiaoH/RepMLP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/repmlp-re-parameterizing-convolutions-into#ran","syntology_url":"https://syntology.ai/paper/2105.01883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01883"}}}},{"paper":"/paper/mlp-mixer-an-all-mlp-architecture-for-vision","slug":"mlp-mixer-an-all-mlp-architecture-for-vision","title":"MLP-Mixer: An all-MLP Architecture for Vision","date":"2021-05-04","arxiv_id":"2105.01601","rows_on_this_dataset":3,"code_links":49,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":134,"samples_ran":114,"samples_constructed":77,"samples_ran_checked":105,"samples_ran_instrument_failed":9,"samples_unverified":20,"pointer_only_for_licence":40,"official":{"repos":["google-research/vision_transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mlp-mixer-an-all-mlp-architecture-for-vision#ran","syntology_url":"https://syntology.ai/paper/2105.01601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01601"}}}},{"paper":"/paper/emerging-properties-in-self-supervised-vision","slug":"emerging-properties-in-self-supervised-vision","title":"Emerging Properties in Self-Supervised Vision Transformers","date":"2021-04-29","arxiv_id":"2104.14294","rows_on_this_dataset":7,"code_links":32,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":20,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/dino"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/emerging-properties-in-self-supervised-vision#ran","syntology_url":"https://syntology.ai/paper/2104.14294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14294"}}}},{"paper":"/paper/with-a-little-help-from-my-friends-nearest","slug":"with-a-little-help-from-my-friends-nearest","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","date":"2021-04-29","arxiv_id":"2104.14548","rows_on_this_dataset":3,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/with-a-little-help-from-my-friends-nearest#ran","syntology_url":"https://syntology.ai/paper/2104.14548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14548"}}}},{"paper":"/paper/semi-supervised-learning-of-visual-features","slug":"semi-supervised-learning-of-visual-features","title":"Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples","date":"2021-04-28","arxiv_id":"2104.13963","rows_on_this_dataset":8,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":21,"samples_ran":19,"samples_constructed":4,"samples_ran_checked":16,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["facebookresearch/suncet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/semi-supervised-learning-of-visual-features#ran","syntology_url":"https://syntology.ai/paper/2104.13963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13963"}}}},{"paper":"/paper/twins-revisiting-spatial-attention-design-in","slug":"twins-revisiting-spatial-attention-design-in","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","date":"2021-04-28","arxiv_id":"2104.13840","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["Meituan-AutoML/Twins"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/twins-revisiting-spatial-attention-design-in#ran","syntology_url":"https://syntology.ai/paper/2104.13840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13840"}}}},{"paper":"/paper/visformer-the-vision-friendly-transformer","slug":"visformer-the-vision-friendly-transformer","title":"Visformer: The Vision-friendly Transformer","date":"2021-04-26","arxiv_id":"2104.12533","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["danczs/Visformer"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visformer-the-vision-friendly-transformer#ran","syntology_url":"https://syntology.ai/paper/2104.12533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12533"}}}},{"paper":"/paper/multiscale-vision-transformers","slug":"multiscale-vision-transformers","title":"Multiscale Vision Transformers","date":"2021-04-22","arxiv_id":"2104.11227","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":26,"samples_ran":13,"samples_constructed":10,"samples_ran_checked":11,"samples_ran_instrument_failed":2,"samples_unverified":13,"pointer_only_for_licence":5,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"paper":"/paper/token-labeling-training-a-85-5-top-1-accuracy","slug":"token-labeling-training-a-85-5-top-1-accuracy","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","date":"2021-04-22","arxiv_id":"2104.10858","rows_on_this_dataset":3,"code_links":7,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["zihangJiang/TokenLabeling"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/token-labeling-training-a-85-5-top-1-accuracy#ran","syntology_url":"https://syntology.ai/paper/2104.10858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10858"}}}},{"paper":"/paper/differentiable-model-compression-via-pseudo","slug":"differentiable-model-compression-via-pseudo","title":"Differentiable Model Compression via Pseudo Quantization Noise","date":"2021-04-20","arxiv_id":"2104.09987","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/distilling-knowledge-via-knowledge-review","slug":"distilling-knowledge-via-knowledge-review","title":"Distilling Knowledge via Knowledge Review","date":"2021-04-19","arxiv_id":"2104.09044","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":2,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":5,"official":{"repos":["Jia-Research-Lab/ReviewKD"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distilling-knowledge-via-knowledge-review#ran","syntology_url":"https://syntology.ai/paper/2104.09044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09044"}}}},{"paper":"/paper/solving-inefficiency-of-self-supervised","slug":"solving-inefficiency-of-self-supervised","title":"Solving Inefficiency of Self-supervised Representation Learning","date":"2021-04-18","arxiv_id":"2104.08760","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["wanggrun/triplet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/solving-inefficiency-of-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2104.08760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08760"}}}},{"paper":"/paper/bnn-bn-training-binary-neural-networks","slug":"bnn-bn-training-binary-neural-networks","title":"\"BNN - BN = ?\": Training Binary Neural Networks without Batch Normalization","date":"2021-04-16","arxiv_id":"2104.08215","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":3,"official":{"repos":["VITA-Group/BNN_NoBN"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bnn-bn-training-binary-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2104.08215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08215"}}}},{"paper":"/paper/polynomial-networks-in-deep-classifiers","slug":"polynomial-networks-in-deep-classifiers","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","date":"2021-04-16","arxiv_id":"2104.07916","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["grigorisg9gr/polynomials-for-augmenting-nns"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/polynomial-networks-in-deep-classifiers#ran","syntology_url":"https://syntology.ai/paper/2104.07916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07916"}}}},{"paper":"/paper/asymmnet-towards-ultralight-convolution","slug":"asymmnet-towards-ultralight-convolution","title":"AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks","date":"2021-04-15","arxiv_id":"2104.07770","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/escaping-the-big-data-paradigm-with-compact","slug":"escaping-the-big-data-paradigm-with-compact","title":"Escaping the Big Data Paradigm with Compact Transformers","date":"2021-04-12","arxiv_id":"2104.05704","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["SHI-Labs/Compact-Transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/escaping-the-big-data-paradigm-with-compact#ran","syntology_url":"https://syntology.ai/paper/2104.05704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05704"}}}},{"paper":"/paper/localvit-bringing-locality-to-vision","slug":"localvit-bringing-locality-to-vision","title":"LocalViT: Bringing Locality to Vision Transformers","date":"2021-04-12","arxiv_id":"2104.05707","rows_on_this_dataset":5,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["ofsoundof/LocalViT"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/localvit-bringing-locality-to-vision#ran","syntology_url":"https://syntology.ai/paper/2104.05707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05707"}}}},{"paper":"/paper/an-empirical-study-of-training-self","slug":"an-empirical-study-of-training-self","title":"An Empirical Study of Training Self-Supervised Vision Transformers","date":"2021-04-05","arxiv_id":"2104.02057","rows_on_this_dataset":7,"code_links":9,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["facebookresearch/moco-v3"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-empirical-study-of-training-self#ran","syntology_url":"https://syntology.ai/paper/2104.02057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02057"}}}},{"paper":"/paper/levit-a-vision-transformer-in-convnet-s","slug":"levit-a-vision-transformer-in-convnet-s","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","date":"2021-04-02","arxiv_id":"2104.01136","rows_on_this_dataset":10,"code_links":12,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":30,"samples_ran":23,"samples_constructed":16,"samples_ran_checked":21,"samples_ran_instrument_failed":2,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["facebookresearch/LeViT","rwightman/pytorch-image-models"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/levit-a-vision-transformer-in-convnet-s#ran","syntology_url":"https://syntology.ai/paper/2104.01136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.01136"}}}},{"paper":"/paper/efficientnetv2-smaller-models-and-faster","slug":"efficientnetv2-smaller-models-and-faster","title":"EfficientNetV2: Smaller Models and Faster Training","date":"2021-04-01","arxiv_id":"2104.00298","rows_on_this_dataset":7,"code_links":26,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":79,"samples_ran":55,"samples_constructed":14,"samples_ran_checked":46,"samples_ran_instrument_failed":9,"samples_unverified":24,"pointer_only_for_licence":13,"official":{"repos":["google/automl"],"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":["community","listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficientnetv2-smaller-models-and-faster#ran","syntology_url":"https://syntology.ai/paper/2104.00298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00298"}}}},{"paper":"/paper/training-multi-bit-quantized-and-binarized","slug":"training-multi-bit-quantized-and-binarized","title":"Training Multi-bit Quantized and Binarized Networks with A Learnable Symmetric Quantizer","date":"2021-04-01","arxiv_id":"2104.00210","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/going-deeper-with-image-transformers","slug":"going-deeper-with-image-transformers","title":"Going deeper with Image Transformers","date":"2021-03-31","arxiv_id":"2103.17239","rows_on_this_dataset":12,"code_links":21,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["rwightman/pytorch-image-models","facebookresearch/deit"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/going-deeper-with-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2103.17239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.17239"}}}},{"paper":"/paper/rethinking-spatial-dimensions-of-vision","slug":"rethinking-spatial-dimensions-of-vision","title":"Rethinking Spatial Dimensions of Vision Transformers","date":"2021-03-30","arxiv_id":"2103.16302","rows_on_this_dataset":4,"code_links":12,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":20,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":10,"pointer_only_for_licence":0,"official":{"repos":["naver-ai/pit"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rethinking-spatial-dimensions-of-vision#ran","syntology_url":"https://syntology.ai/paper/2103.16302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16302"}}}},{"paper":"/paper/2103-15358","slug":"2103-15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","date":"2021-03-29","arxiv_id":"2103.15358","rows_on_this_dataset":6,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["microsoft/vision-longformer"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/2103-15358#ran","syntology_url":"https://syntology.ai/paper/2103.15358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15358"}}}},{"paper":"/paper/complementary-relation-contrastive","slug":"complementary-relation-contrastive","title":"Complementary Relation Contrastive Distillation","date":"2021-03-29","arxiv_id":"2103.16367","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/complementary-relation-contrastive#ran","syntology_url":"https://syntology.ai/paper/2103.16367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16367"}}}},{"paper":"/paper/cvt-introducing-convolutions-to-vision","slug":"cvt-introducing-convolutions-to-vision","title":"CvT: Introducing Convolutions to Vision Transformers","date":"2021-03-29","arxiv_id":"2103.15808","rows_on_this_dataset":7,"code_links":16,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":47,"samples_ran":39,"samples_constructed":19,"samples_ran_checked":36,"samples_ran_instrument_failed":3,"samples_unverified":8,"pointer_only_for_licence":8,"official":{"repos":["microsoft/CvT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["listed","named_in_paper","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cvt-introducing-convolutions-to-vision#ran","syntology_url":"https://syntology.ai/paper/2103.15808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15808"}}}},{"paper":"/paper/2103-14899","slug":"2103-14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","date":"2021-03-27","arxiv_id":"2103.14899","rows_on_this_dataset":4,"code_links":15,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":26,"samples_ran":17,"samples_constructed":10,"samples_ran_checked":17,"samples_ran_instrument_failed":0,"samples_unverified":9,"pointer_only_for_licence":0,"official":{"repos":["IBM/CrossViT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/2103-14899#ran","syntology_url":"https://syntology.ai/paper/2103.14899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14899"}}}},{"paper":"/paper/swin-transformer-hierarchical-vision","slug":"swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","arxiv_id":"2103.14030","rows_on_this_dataset":3,"code_links":80,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":207,"samples_ran":123,"samples_constructed":45,"samples_ran_checked":82,"samples_ran_instrument_failed":41,"samples_unverified":84,"pointer_only_for_licence":45,"official":{"repos":["microsoft/Swin-Transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/swin-transformer-hierarchical-vision#ran","syntology_url":"https://syntology.ai/paper/2103.14030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14030"}}}},{"paper":"/paper/automix-unveiling-the-power-of-mixup","slug":"automix-unveiling-the-power-of-mixup","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","date":"2021-03-24","arxiv_id":"2103.13027","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["Westlake-AI/openmixup"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/automix-unveiling-the-power-of-mixup#ran","syntology_url":"https://syntology.ai/paper/2103.13027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13027"}}}},{"paper":"/paper/bossnas-exploring-hybrid-cnn-transformers","slug":"bossnas-exploring-hybrid-cnn-transformers","title":"BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search","date":"2021-03-23","arxiv_id":"2103.12424","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/scaling-local-self-attention-for-parameter","slug":"scaling-local-self-attention-for-parameter","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","date":"2021-03-23","arxiv_id":"2103.12731","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":20,"samples_ran":18,"samples_constructed":4,"samples_ran_checked":11,"samples_ran_instrument_failed":7,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-local-self-attention-for-parameter#ran","syntology_url":"https://syntology.ai/paper/2103.12731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12731"}}}},{"paper":"/paper/deepvit-towards-deeper-vision-transformer","slug":"deepvit-towards-deeper-vision-transformer","title":"DeepViT: Towards Deeper Vision Transformer","date":"2021-03-22","arxiv_id":"2103.11886","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["zhoudaquan/dvit_repo"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deepvit-towards-deeper-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2103.11886","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11886"}}}},{"paper":"/paper/incorporating-convolution-designs-into-visual","slug":"incorporating-convolution-designs-into-visual","title":"Incorporating Convolution Designs into Visual Transformers","date":"2021-03-22","arxiv_id":"2103.11816","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":9,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["coeusguo/ceit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/incorporating-convolution-designs-into-visual#ran","syntology_url":"https://syntology.ai/paper/2103.11816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11816"}}}},{"paper":"/paper/convit-improving-vision-transformers-with","slug":"convit-improving-vision-transformers-with","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","date":"2021-03-19","arxiv_id":"2103.10697","rows_on_this_dataset":6,"code_links":9,"syntology":null},{"paper":"/paper/scalable-visual-transformers-with","slug":"scalable-visual-transformers-with","title":"Scalable Vision Transformers with Hierarchical Pooling","date":"2021-03-19","arxiv_id":"2103.10619","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["MonashAI/HVT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scalable-visual-transformers-with#ran","syntology_url":"https://syntology.ai/paper/2103.10619","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10619"}}}},{"paper":"/paper/self-supervised-classification-network","slug":"self-supervised-classification-network","title":"Self-Supervised Classification Network","date":"2021-03-19","arxiv_id":"2103.10994","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/trivialaugment-tuning-free-yet-state-of-the","slug":"trivialaugment-tuning-free-yet-state-of-the","title":"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation","date":"2021-03-18","arxiv_id":"2103.10158","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/multi-prize-lottery-ticket-hypothesis-finding-1","slug":"multi-prize-lottery-ticket-hypothesis-finding-1","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","date":"2021-03-17","arxiv_id":"2103.09377","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/revisiting-resnets-improved-training-and","slug":"revisiting-resnets-improved-training-and","title":"Revisiting ResNets: Improved Training and Scaling Strategies","date":"2021-03-13","arxiv_id":"2103.07579","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/involution-inverting-the-inherence-of","slug":"involution-inverting-the-inherence-of","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","date":"2021-03-10","arxiv_id":"2103.06255","rows_on_this_dataset":5,"code_links":13,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":7,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["d-li14/involution"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/involution-inverting-the-inherence-of#ran","syntology_url":"https://syntology.ai/paper/2103.06255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06255"}}}},{"paper":"/paper/barlow-twins-self-supervised-learning-via","slug":"barlow-twins-self-supervised-learning-via","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","date":"2021-03-04","arxiv_id":"2103.03230","rows_on_this_dataset":3,"code_links":24,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":26,"samples_ran":21,"samples_constructed":6,"samples_ran_checked":15,"samples_ran_instrument_failed":6,"samples_unverified":5,"pointer_only_for_licence":10,"official":{"repos":["facebookresearch/barlowtwins"],"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":["community","listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/barlow-twins-self-supervised-learning-via#ran","syntology_url":"https://syntology.ai/paper/2103.03230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03230"}}}},{"paper":"/paper/perceiver-general-perception-with-iterative","slug":"perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","arxiv_id":"2103.03206","rows_on_this_dataset":2,"code_links":12,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":55,"samples_ran":41,"samples_constructed":20,"samples_ran_checked":30,"samples_ran_instrument_failed":11,"samples_unverified":14,"pointer_only_for_licence":11,"official":{"repos":["deepmind/deepmind-research"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["community","listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/perceiver-general-perception-with-iterative#ran","syntology_url":"https://syntology.ai/paper/2103.03206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03206"}}}},{"paper":"/paper/self-supervised-pretraining-of-visual","slug":"self-supervised-pretraining-of-visual","title":"Self-supervised Pretraining of Visual Features in the Wild","date":"2021-03-02","arxiv_id":"2103.01988","rows_on_this_dataset":7,"code_links":1,"syntology":null},{"paper":"/paper/transformer-in-transformer","slug":"transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","arxiv_id":"2103.00112","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":24,"samples_ran":16,"samples_constructed":12,"samples_ran_checked":15,"samples_ran_instrument_failed":1,"samples_unverified":8,"pointer_only_for_licence":5,"official":{"repos":["huawei-noah/CV-backbones"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/transformer-in-transformer#ran","syntology_url":"https://syntology.ai/paper/2103.00112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00112"}}}}],"record_sha256":"c7ff919baf814f1fdac62ef771c0d819c7a665dda25d237eab9ef045edae6e62","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}