{"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/10","list_of":"/method/vision-transformer","method":"Vision Transformer","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":10,"pages_in_order":22,"rows_per_page":100,"rows":[901,1000],"of":2144,"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","prev":"/method/vision-transformer/papers/9","next":"/method/vision-transformer/papers/11","papers":[{"paper":"/paper/pl-fscil-harnessing-the-power-of-prompts-for","slug":"pl-fscil-harnessing-the-power-of-prompts-for","title":"PL-FSCIL: Harnessing the Power of Prompts for Few-Shot Class-Incremental Learning","date":"2024-01-26","arxiv_id":"2401.14807","n_code_links":1,"syntology":null},{"paper":"/paper/cross-domain-few-shot-learning-via-adaptive","slug":"cross-domain-few-shot-learning-via-adaptive","title":"Cross-Domain Few-Shot Learning via Adaptive Transformer Networks","date":"2024-01-25","arxiv_id":"2401.13987","n_code_links":1,"syntology":null},{"paper":"/paper/grounded-sam-assembling-open-world-models-for","slug":"grounded-sam-assembling-open-world-models-for","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","date":"2024-01-25","arxiv_id":"2401.14159","n_code_links":5,"syntology":{"ran":15,"of":15,"n_ran_checked":10,"n_instrument":5,"unverified":0,"pointer_only":5,"phrase":"15 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["IDEA-Research/Grounded-Segment-Anything"],"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/convolutional-initialization-for-data","slug":"convolutional-initialization-for-data","title":"Convolutional Initialization for Data-Efficient Vision Transformers","date":"2024-01-23","arxiv_id":"2401.12511","n_code_links":1,"syntology":null},{"paper":"/paper/datus-2-data-driven-unsupervised-semantic","slug":"datus-2-data-driven-unsupervised-semantic","title":"DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer","date":"2024-01-23","arxiv_id":"2401.12820","n_code_links":1,"syntology":null},{"paper":null,"slug":"el-vit-probing-vision-transformer-with","title":"EL-VIT: Probing Vision Transformer with Interactive Visualization","date":"2024-01-23","arxiv_id":"2401.12666","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-qcnn-lstm-for-disability","title":"Evaluation of QCNN-LSTM for Disability Forecasting in Multiple Sclerosis Using Sequential Multisequence MRI","date":"2024-01-22","arxiv_id":"2401.12132","n_code_links":0,"syntology":null},{"paper":"/paper/ondev-lct-on-device-lightweight-convolutional","slug":"ondev-lct-on-device-lightweight-convolutional","title":"OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning","date":"2024-01-22","arxiv_id":"2401.11652","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-benchmark-for-few-shot-semantic","slug":"a-novel-benchmark-for-few-shot-semantic","title":"A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models","date":"2024-01-20","arxiv_id":"2401.11311","n_code_links":1,"syntology":null},{"paper":"/paper/denguenet-dengue-prediction-using","slug":"denguenet-dengue-prediction-using","title":"DengueNet: Dengue Prediction using Spatiotemporal Satellite Imagery for Resource-Limited Countries","date":"2024-01-20","arxiv_id":"2401.11114","n_code_links":1,"syntology":null},{"paper":null,"slug":"photobot-reference-guided-interactive","title":"PhotoBot: Reference-Guided Interactive Photography via Natural Language","date":"2024-01-19","arxiv_id":"2401.11061","n_code_links":0,"syntology":null},{"paper":null,"slug":"hcvp-leveraging-hierarchical-contrastive","title":"HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization","date":"2024-01-18","arxiv_id":"2401.09716","n_code_links":0,"syntology":null},{"paper":null,"slug":"reconstructing-the-invisible-video-frame","title":"Reconstructing the Invisible: Video Frame Restoration through Siamese Masked Conditional Variational Autoencoder","date":"2024-01-18","arxiv_id":"2401.10402","n_code_links":0,"syntology":null},{"paper":"/paper/supervised-fine-tuning-in-turn-improves","slug":"supervised-fine-tuning-in-turn-improves","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","date":"2024-01-18","arxiv_id":"2401.10222","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":10,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["tencentarc/visft"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/ct-liver-segmentation-via-pvt-based-encoding","slug":"ct-liver-segmentation-via-pvt-based-encoding","title":"CT Liver Segmentation via PVT-based Encoding and Refined Decoding","date":"2024-01-17","arxiv_id":"2401.09630","n_code_links":1,"syntology":null},{"paper":null,"slug":"b-cos-aligned-transformers-learn-human","title":"B-Cos Aligned Transformers Learn Human-Interpretable Features","date":"2024-01-16","arxiv_id":"2401.08868","n_code_links":0,"syntology":null},{"paper":null,"slug":"mobile-contactless-palmprint-recognition-use","title":"Mobile Contactless Palmprint Recognition: Use of Multiscale, Multimodel Embeddings","date":"2024-01-16","arxiv_id":"2401.08111","n_code_links":0,"syntology":null},{"paper":"/paper/scalable-pre-training-of-large-autoregressive","slug":"scalable-pre-training-of-large-autoregressive","title":"Scalable Pre-training of Large Autoregressive Image Models","date":"2024-01-16","arxiv_id":"2401.08541","n_code_links":2,"syntology":null},{"paper":"/paper/statistical-test-for-attention-map-in-vision","slug":"statistical-test-for-attention-map-in-vision","title":"Statistical Test for Attention Map in Vision Transformer","date":"2024-01-16","arxiv_id":"2401.08169","n_code_links":1,"syntology":null},{"paper":"/paper/a-deep-hierarchical-feature-sparse-framework","slug":"a-deep-hierarchical-feature-sparse-framework","title":"A Deep Hierarchical Feature Sparse Framework for Occluded Person Re-Identification","date":"2024-01-15","arxiv_id":"2401.07469","n_code_links":0,"syntology":null},{"paper":"/paper/image-similarity-using-an-ensemble-of-context","slug":"image-similarity-using-an-ensemble-of-context","title":"Image Similarity using An Ensemble of Context-Sensitive Models","date":"2024-01-15","arxiv_id":"2401.07951","n_code_links":1,"syntology":null},{"paper":null,"slug":"updp-a-unified-progressive-depth-pruner-for","title":"UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer","date":"2024-01-12","arxiv_id":"2401.06426","n_code_links":0,"syntology":null},{"paper":"/paper/video-super-resolution-transformer-with","slug":"video-super-resolution-transformer-with","title":"Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention","date":"2024-01-12","arxiv_id":"2401.06312","n_code_links":1,"syntology":null},{"paper":null,"slug":"brain-tumor-radiogenomic-classification","title":"Brain Tumor Radiogenomic Classification","date":"2024-01-11","arxiv_id":"2401.09471","n_code_links":0,"syntology":null},{"paper":null,"slug":"cosseggaussians-compact-and-swift-scene","title":"Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation","date":"2024-01-11","arxiv_id":"2401.05925","n_code_links":0,"syntology":null},{"paper":"/paper/surgical-dino-adapter-learning-of-foundation","slug":"surgical-dino-adapter-learning-of-foundation","title":"Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery","date":"2024-01-11","arxiv_id":"2401.06013","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["beileicui/surgicaldino"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"adaptive-avg-pooling-based-attention-vision","title":"Adaptive-avg-pooling based Attention Vision Transformer for Face Anti-spoofing","date":"2024-01-10","arxiv_id":"2401.04953","n_code_links":0,"syntology":null},{"paper":null,"slug":"derm-t2im-harnessing-synthetic-skin-lesion","title":"Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN","date":"2024-01-10","arxiv_id":"2401.05159","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-fine-tuning-with-domain-adaptation","title":"Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer","date":"2024-01-10","arxiv_id":"2401.05126","n_code_links":0,"syntology":null},{"paper":null,"slug":"skin-cancer-segmentation-and-classification","title":"Skin Cancer Segmentation and Classification Using Vision Transformer for Automatic Analysis in Dermatoscopy-based Non-invasive Digital System","date":"2024-01-09","arxiv_id":"2401.04746","n_code_links":0,"syntology":null},{"paper":null,"slug":"waveletformernet-a-transformer-based-wavelet","title":"WaveletFormerNet: A Transformer-based Wavelet Network for Real-world Non-homogeneous and Dense Fog Removal","date":"2024-01-09","arxiv_id":"2401.04550","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-guided-erasing-a-novel-augmentation","title":"Attention-Guided Erasing: A Novel Augmentation Method for Enhancing Downstream Breast Density Classification","date":"2024-01-08","arxiv_id":"2401.03912","n_code_links":0,"syntology":null},{"paper":"/paper/lf-vit-reducing-spatial-redundancy-in-vision","slug":"lf-vit-reducing-spatial-redundancy-in-vision","title":"LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition","date":"2024-01-08","arxiv_id":"2402.00033","n_code_links":1,"syntology":{"ran":11,"of":18,"n_ran_checked":8,"n_instrument":3,"unverified":7,"pointer_only":18,"phrase":"11 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; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["edgeai1/lf-vit"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"realism-in-action-anomaly-aware-diagnosis-of","title":"Realism in Action: Anomaly-Aware Diagnosis of Brain Tumors from Medical Images Using YOLOv8 and DeiT","date":"2024-01-06","arxiv_id":"2401.03302","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-random-ensemble-of-encrypted-models-for","title":"A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examples","date":"2024-01-05","arxiv_id":"2401.02633","n_code_links":0,"syntology":null},{"paper":"/paper/denoising-vision-transformers","slug":"denoising-vision-transformers","title":"Denoising Vision Transformers","date":"2024-01-05","arxiv_id":"2401.02957","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Jiawei-Yang/Denoising-ViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/prompt-driven-latent-domain-generalization","slug":"prompt-driven-latent-domain-generalization","title":"Prompt-driven Latent Domain Generalization for Medical Image Classification","date":"2024-01-05","arxiv_id":"2401.03002","n_code_links":2,"syntology":null},{"paper":null,"slug":"spformer-enhancing-vision-transformer-with","title":"SPFormer: Enhancing Vision Transformer with Superpixel Representation","date":"2024-01-05","arxiv_id":"2401.02931","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-method-to-enhance-pneumonia-detection","title":"A novel method to enhance pneumonia detection via a model-level ensembling of CNN and vision transformer","date":"2024-01-04","arxiv_id":"2401.02358","n_code_links":0,"syntology":null},{"paper":"/paper/classwise-sam-adapter-parameter-efficient","slug":"classwise-sam-adapter-parameter-efficient","title":"ClassWise-SAM-Adapter: Parameter Efficient Fine-tuning Adapts Segment Anything to SAR Domain for Semantic Segmentation","date":"2024-01-04","arxiv_id":"2401.02326","n_code_links":1,"syntology":null},{"paper":null,"slug":"fulllora-at-efficiently-boosting-the","title":"FullLoRA-AT: Efficiently Boosting the Robustness of Pretrained Vision Transformers","date":"2024-01-03","arxiv_id":"2401.01752","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-robust-semantic-segmentation-against","title":"Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement","date":"2024-01-03","arxiv_id":"2401.01750","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-transformer-s-robustness-and","title":"A Novel Transformer-Based Self-Supervised Learning Method to Enhance Photoplethysmogram Signal Artifact Detection","date":"2024-01-02","arxiv_id":"2401.01013","n_code_links":0,"syntology":null},{"paper":"/paper/boosting-image-quality-assessment-through","slug":"boosting-image-quality-assessment-through","title":"Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/class-tokens-infusion-for-weakly-supervised","slug":"class-tokens-infusion-for-weakly-supervised","title":"Class Tokens Infusion for Weakly Supervised Semantic Segmentation","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"deit-lt-distillation-strikes-back-for-vision-1","title":"DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets","date":"2024-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/flexible-biometrics-recognition-bridging-the","slug":"flexible-biometrics-recognition-bridging-the","title":"Flexible Biometrics Recognition: Bridging the Multimodality Gap through Attention Alignment and Prompt Tuning","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/h-vit-a-hierarchical-vision-transformer-for","slug":"h-vit-a-hierarchical-vision-transformer-for","title":"H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"kd-detr-knowledge-distillation-for-detection","title":"KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling","date":"2024-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learn-to-rectify-the-bias-of-clip-for","slug":"learn-to-rectify-the-bias-of-clip-for","title":"Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/linguistic-aware-patch-slimming-framework-for","slug":"linguistic-aware-patch-slimming-framework-for","title":"Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/pre-training-vision-models-with-mandelbulb","slug":"pre-training-vision-models-with-mandelbulb","title":"Pre-training Vision Models with Mandelbulb Variations","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/slowformer-adversarial-attack-on-compute-and","slug":"slowformer-adversarial-attack-on-compute-and","title":"SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"time-memory-and-parameter-efficient-visual-1","title":"Time- Memory- and Parameter-Efficient Visual Adaptation","date":"2024-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/training-vision-transformers-for-semi","slug":"training-vision-transformers-for-semi","title":"Training Vision Transformers for Semi-Supervised Semantic Segmentation","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/unlocking-the-potential-of-pre-trained-vision","slug":"unlocking-the-potential-of-pre-trained-vision","title":"Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-local-representations-of-self","title":"Analyzing Local Representations of Self-supervised Vision Transformers","date":"2023-12-31","arxiv_id":"2401.00463","n_code_links":0,"syntology":null},{"paper":"/paper/multiscale-vision-transformers-meet-bipartite","slug":"multiscale-vision-transformers-meet-bipartite","title":"Multiscale Vision Transformers meet Bipartite Matching for efficient single-stage Action Localization","date":"2023-12-29","arxiv_id":"2312.17686","n_code_links":1,"syntology":null},{"paper":"/paper/learning-vision-from-models-rivals-learning","slug":"learning-vision-from-models-rivals-learning","title":"Learning Vision from Models Rivals Learning Vision from Data","date":"2023-12-28","arxiv_id":"2312.17742","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/syn-rep-learn"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"roi-aware-multiscale-cross-attention-vision","title":"ROI-Aware Multiscale Cross-Attention Vision Transformer for Pest Image Identification","date":"2023-12-28","arxiv_id":"2312.16914","n_code_links":0,"syntology":null},{"paper":"/paper/weed-mapping-in-multispectral-drone-imagery","slug":"weed-mapping-in-multispectral-drone-imagery","title":"Weed mapping in multispectral drone imagery using lightweight vision transformers","date":"2023-12-28","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/group-multi-view-transformer-for-3d-shape","slug":"group-multi-view-transformer-for-3d-shape","title":"Group Multi-View Transformer for 3D Shape Analysis with Spatial Encoding","date":"2023-12-27","arxiv_id":"2312.16477","n_code_links":1,"syntology":null},{"paper":"/paper/c2t-net-channel-aware-cross-fused-transformer","slug":"c2t-net-channel-aware-cross-fused-transformer","title":"C2T-Net: Channel-Aware Cross-Fused Transformer-Style Networks for Pedestrian Attribute Recognition","date":"2023-12-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/langsplat-3d-language-gaussian-splatting","slug":"langsplat-3d-language-gaussian-splatting","title":"LangSplat: 3D Language Gaussian Splatting","date":"2023-12-26","arxiv_id":"2312.16084","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["minghanqin/LangSplat"],"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":["official"]}}},{"paper":"/paper/deep-structure-and-attention-aware-subspace","slug":"deep-structure-and-attention-aware-subspace","title":"Deep Structure and Attention Aware Subspace Clustering","date":"2023-12-25","arxiv_id":"2312.15577","n_code_links":1,"syntology":null},{"paper":null,"slug":"partial-fine-tuning-a-successor-to-full-fine","title":"Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers","date":"2023-12-25","arxiv_id":"2312.15681","n_code_links":0,"syntology":null},{"paper":"/paper/cr-sam-curvature-regularized-sharpness-aware","slug":"cr-sam-curvature-regularized-sharpness-aware","title":"CR-SAM: Curvature Regularized Sharpness-Aware Minimization","date":"2023-12-21","arxiv_id":"2312.13555","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":5,"n_instrument":2,"unverified":4,"pointer_only":11,"phrase":"7 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["trustaiot/cr-sam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/context-disentangling-and-prototype","slug":"context-disentangling-and-prototype","title":"Context Disentangling and Prototype Inheriting for Robust Visual Grounding","date":"2023-12-19","arxiv_id":"2312.11967","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrating-human-vision-perception-in-vision","title":"Integrating Human Vision Perception in Vision Transformers for Classifying Waste Items","date":"2023-12-19","arxiv_id":"2312.12143","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-segmentation-of-colonoscopy","title":"Unsupervised Segmentation of Colonoscopy Images","date":"2023-12-19","arxiv_id":"2312.12599","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-vocabulary-semantic-scene-sketch","title":"Open Vocabulary Semantic Scene Sketch Understanding","date":"2023-12-18","arxiv_id":"2312.12463","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-case-study-of-image-enhancement-algorithms","title":"A Case Study of Image Enhancement Algorithms' Effectiveness of Improving Neural Networks' Performance on Adverse Images","date":"2023-12-15","arxiv_id":"2312.09509","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-neural-network-training-a-brief","slug":"accelerating-neural-network-training-a-brief","title":"Accelerating Neural Network Training: A Brief Review","date":"2023-12-15","arxiv_id":"2312.10024","n_code_links":1,"syntology":null},{"paper":"/paper/auto-prox-training-free-vision-transformer","slug":"auto-prox-training-free-vision-transformer","title":"Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery","date":"2023-12-14","arxiv_id":"2312.09059","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lilujunai/auto-prox-aaai24"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/factorization-vision-transformer-modeling","slug":"factorization-vision-transformer-modeling","title":"Factorization Vision Transformer: Modeling Long Range Dependency with Local Window Cost","date":"2023-12-14","arxiv_id":"2312.08614","n_code_links":1,"syntology":null},{"paper":null,"slug":"guided-diffusion-from-self-supervised","title":"Guided Diffusion from Self-Supervised Diffusion Features","date":"2023-12-14","arxiv_id":"2312.08825","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-multi-object-pose-estimation-using","title":"Efficient Multi-Object Pose Estimation using Multi-Resolution Deformable Attention and Query Aggregation","date":"2023-12-13","arxiv_id":"2312.08268","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformer-based-deep-learning-for","title":"Vision Transformer-Based Deep Learning for Histologic Classification of Endometrial Cancer","date":"2023-12-13","arxiv_id":"2312.08479","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-deep-learning-classifiers-for","title":"Benchmarking Deep Learning Classifiers for SAR Automatic Target Recognition","date":"2023-12-12","arxiv_id":"2312.06940","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-plain-vit-reconstruction-for-multi","slug":"exploring-plain-vit-reconstruction-for-multi","title":"Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection","date":"2023-12-12","arxiv_id":"2312.07495","n_code_links":1,"syntology":null},{"paper":"/paper/mixed-pseudo-labels-for-semi-supervised","slug":"mixed-pseudo-labels-for-semi-supervised","title":"Mixed Pseudo Labels for Semi-Supervised Object Detection","date":"2023-12-12","arxiv_id":"2312.07006","n_code_links":1,"syntology":null},{"paper":"/paper/pre-trained-universal-medical-image","slug":"pre-trained-universal-medical-image","title":"Building Universal Foundation Models for Medical Image Analysis with Spatially Adaptive Networks","date":"2023-12-12","arxiv_id":"2312.07630","n_code_links":1,"syntology":null},{"paper":"/paper/u-mixformer-unet-like-transformer-with-mix","slug":"u-mixformer-unet-like-transformer-with-mix","title":"U-MixFormer: UNet-like Transformer with Mix-Attention for Efficient Semantic Segmentation","date":"2023-12-11","arxiv_id":"2312.06272","n_code_links":1,"syntology":null},{"paper":"/paper/from-static-to-dynamic-adapting-landmark-1","slug":"from-static-to-dynamic-adapting-landmark-1","title":"From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos","date":"2023-12-09","arxiv_id":"2312.05447","n_code_links":2,"syntology":{"ran":11,"of":14,"n_ran_checked":11,"n_instrument":0,"unverified":3,"pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["FER-LMC/S2D","msa-lmc/s2d"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"identifying-and-mitigating-model-failures","title":"Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation","date":"2023-12-09","arxiv_id":"2312.05464","n_code_links":0,"syntology":null},{"paper":"/paper/reconstructing-hands-in-3d-with-transformers","slug":"reconstructing-hands-in-3d-with-transformers","title":"Reconstructing Hands in 3D with Transformers","date":"2023-12-08","arxiv_id":"2312.05251","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, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"an-unsupervised-approach-towards-promptable","title":"An unsupervised approach towards promptable defect segmentation in laser-based additive manufacturing by Segment Anything","date":"2023-12-07","arxiv_id":"2312.04063","n_code_links":0,"syntology":null},{"paper":"/paper/deepfidelity-perceptual-forgery-fidelity","slug":"deepfidelity-perceptual-forgery-fidelity","title":"DeepFidelity: Perceptual Forgery Fidelity Assessment for Deepfake Detection","date":"2023-12-07","arxiv_id":"2312.04961","n_code_links":2,"syntology":null},{"paper":"/paper/docbinformer-a-two-level-transformer-network","slug":"docbinformer-a-two-level-transformer-network","title":"DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarization","date":"2023-12-06","arxiv_id":"2312.03568","n_code_links":1,"syntology":null},{"paper":"/paper/lite-mind-towards-efficient-and-versatile","slug":"lite-mind-towards-efficient-and-versatile","title":"Lite-Mind: Towards Efficient and Robust Brain Representation Network","date":"2023-12-06","arxiv_id":"2312.03781","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":6,"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":{"repos":["gongzix/lite-mind"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"when-an-image-is-worth-1024-x-1024-words-a","title":"When an Image is Worth 1,024 x 1,024 Words: A Case Study in Computational Pathology","date":"2023-12-06","arxiv_id":"2312.03558","n_code_links":0,"syntology":null},{"paper":null,"slug":"r3d-swin-use-shifted-window-attention-for","title":"R3D-SWIN:Use Shifted Window Attention for Single-View 3D Reconstruction","date":"2023-12-05","arxiv_id":"2312.02725","n_code_links":0,"syntology":null},{"paper":null,"slug":"upocr-towards-unified-pixel-level-ocr","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","date":"2023-12-05","arxiv_id":"2312.02694","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-literature-review-on-sweet","title":"A Comprehensive Literature Review on Sweet Orange Leaf Diseases","date":"2023-12-04","arxiv_id":"2312.01756","n_code_links":0,"syntology":null},{"paper":"/paper/diffit-diffusion-vision-transformers-for","slug":"diffit-diffusion-vision-transformers-for","title":"DiffiT: Diffusion Vision Transformers for Image Generation","date":"2023-12-04","arxiv_id":"2312.02139","n_code_links":1,"syntology":{"ran":20,"of":25,"n_ran_checked":13,"n_instrument":7,"unverified":5,"pointer_only":25,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified","official":{"repos":["nvlabs/diffit"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-efficient-unsupervised-satellite","slug":"learning-efficient-unsupervised-satellite","title":"Learning Efficient Unsupervised Satellite Image-based Building Damage Detection","date":"2023-12-04","arxiv_id":"2312.01576","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-image-restoration-guided-by-robust","title":"Multi-task Image Restoration Guided By Robust DINO Features","date":"2023-12-04","arxiv_id":"2312.01677","n_code_links":0,"syntology":null},{"paper":null,"slug":"srtransgan-image-super-resolution-using","title":"SRTransGAN: Image Super-Resolution using Transformer based Generative Adversarial Network","date":"2023-12-04","arxiv_id":"2312.01999","n_code_links":0,"syntology":null},{"paper":null,"slug":"universal-deoxidation-of-semiconductor","title":"Universal Deoxidation of Semiconductor Substrates Assisted by Machine-Learning and Real-Time-Feedback-Control","date":"2023-12-04","arxiv_id":"2312.01662","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-report-generation-for-1","slug":"automatic-report-generation-for-1","title":"Automatic Report Generation for Histopathology images using pre-trained Vision Transformers and BERT","date":"2023-12-03","arxiv_id":"2312.01435","n_code_links":1,"syntology":null}],"record_sha256":"4b356cdd267b1052a178b85e3ef5ca6ea1636d25540689ddbd19b49e6a2b1eb2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}