{"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/deit","slug":"deit","name":"DeiT","full_name":"Data-efficient Image Transformer","full_name_withheld":false,"description_markdown":"A **Data-Efficient Image Transformer** is a type of [Vision Transformer](https://paperswithcode.com/method/vision-transformer) for image classification tasks. The model is trained using a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2012.12877v2","title":"Training data-efficient image transformers & distillation through attention","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/facebookresearch/deit/blob/2aefd8fc8634d099c1495ce9dba2b6c6a921d611/models.py#L16","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Models","url":"/methods/category/image-models","pwc_aliases":[]}],"n_papers_tagged":93,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/dart-differentiable-dynamic-adaptive-region","slug":"dart-differentiable-dynamic-adaptive-region","title":"DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Transformer and Mamba","date":"2025-06-12","arxiv_id":"2506.10390","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-attention-required-for-transformer","title":"Is Attention Required for Transformer Inference? Explore Function-preserving Attention Replacement","date":"2025-05-24","arxiv_id":"2505.21535","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-based-identification-of-4","title":"Deep learning-based identification of precipitation clouds from all-sky camera data for observatory safety","date":"2025-03-24","arxiv_id":"2503.18670","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-deepfake-image-detection-a","title":"CAE-Net: Generalized Deepfake Image Detection using Convolution and Attention Mechanisms with Spatial and Frequency Domain Features","date":"2025-02-15","arxiv_id":"2502.10682","n_code_links":0,"syntology":null},{"paper":null,"slug":"mix-qvit-mixed-precision-vision-transformer","title":"Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity","date":"2025-01-10","arxiv_id":"2501.06357","n_code_links":0,"syntology":null},{"paper":null,"slug":"adventurer-optimizing-vision-mamba","title":"Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/training-noise-token-pruning","slug":"training-noise-token-pruning","title":"Training Noise Token Pruning","date":"2024-11-27","arxiv_id":"2411.18092","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalable-iterative-pruning-of-large-language","title":"Scalable iterative pruning of large language and vision models using block coordinate descent","date":"2024-11-26","arxiv_id":"2411.17796","n_code_links":0,"syntology":null},{"paper":"/paper/pqv-mobile-a-combined-pruning-and","slug":"pqv-mobile-a-combined-pruning-and","title":"PQV-Mobile: A Combined Pruning and Quantization Toolkit to Optimize Vision Transformers for Mobile Applications","date":"2024-08-15","arxiv_id":"2408.08437","n_code_links":1,"syntology":null},{"paper":"/paper/mixed-non-linear-quantization-for-vision","slug":"mixed-non-linear-quantization-for-vision","title":"Mixed Non-linear Quantization for Vision Transformers","date":"2024-07-26","arxiv_id":"2407.18437","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-distillation-to-effectively-attain","slug":"knowledge-distillation-to-effectively-attain","title":"Knowledge distillation to effectively attain both region-of-interest and global semantics from an image where multiple objects appear","date":"2024-07-11","arxiv_id":"2407.08257","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-transformers-for-weakly-supervised","slug":"leveraging-transformers-for-weakly-supervised","title":"Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos","date":"2024-07-08","arxiv_id":"2407.06018","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-depression-and-anxiety-risk-in","title":"Predicting Depression and Anxiety Risk in Dutch Neighborhoods from Street-View Images","date":"2024-06-27","arxiv_id":"2407.09547","n_code_links":0,"syntology":null},{"paper":"/paper/liere-generalizing-rotary-position-encodings","slug":"liere-generalizing-rotary-position-encodings","title":"LieRE: Generalizing Rotary Position Encodings","date":"2024-06-14","arxiv_id":"2406.10322","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["stanford-aimi/liere"],"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":["official"]}}},{"paper":"/paper/decomposing-and-interpreting-image","slug":"decomposing-and-interpreting-image","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","date":"2024-06-03","arxiv_id":"2406.01583","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":6,"n_instrument":4,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["sriramb-98/vit-decompose"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-general-and-efficient-training-for","slug":"a-general-and-efficient-training-for","title":"A General and Efficient Training for Transformer via Token Expansion","date":"2024-03-31","arxiv_id":"2404.00672","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":2,"n_instrument":5,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["osilly/tokenexpansion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-criteria-token-fusion-with-one-step","slug":"multi-criteria-token-fusion-with-one-step","title":"Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers","date":"2024-03-15","arxiv_id":"2403.10030","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mlvlab/mctf"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mptq-vit-mixed-precisionpost","title":"MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer","date":"2024-01-26","arxiv_id":"2401.14895","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-and-recognizing-characters-in-greek","title":"Detecting and recognizing characters in Greek papyri with YOLOv8, DeiT and SimCLR","date":"2024-01-23","arxiv_id":"2401.12513","n_code_links":0,"syntology":null},{"paper":null,"slug":"lrp-qvit-mixed-precision-vision-transformer","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","date":"2024-01-20","arxiv_id":"2401.11243","n_code_links":0,"syntology":null},{"paper":"/paper/vision-mamba-efficient-visual-representation","slug":"vision-mamba-efficient-visual-representation","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","date":"2024-01-17","arxiv_id":"2401.09417","n_code_links":15,"syntology":{"ran":8,"of":13,"n_ran_checked":7,"n_instrument":1,"unverified":5,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hustvl/vim"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":null,"slug":"token-propagation-controller-for-efficient","title":"TPC-ViT: Token Propagation Controller for Efficient Vision Transformer","date":"2024-01-03","arxiv_id":"2401.01470","n_code_links":0,"syntology":null},{"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":null,"slug":"bridging-the-gaps-between-token-pruning-and","title":"Bridging The Gaps Between Token Pruning and Full Pre-training via Masked Fine-tuning","date":"2023-10-26","arxiv_id":"2310.17177","n_code_links":0,"syntology":null},{"paper":null,"slug":"usdc-unified-static-and-dynamic-compression","title":"USDC: Unified Static and Dynamic Compression for Visual Transformer","date":"2023-10-17","arxiv_id":"2310.11117","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-vision-transformers-based-on","title":"Accelerating Vision Transformers Based on Heterogeneous Attention Patterns","date":"2023-10-11","arxiv_id":"2310.07664","n_code_links":0,"syntology":null},{"paper":null,"slug":"ewastenet-a-two-stream-data-efficient-image","title":"EWasteNet: A Two-Stream Data Efficient Image Transformer Approach for E-Waste Classification","date":"2023-09-28","arxiv_id":"2311.12823","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-dimensional-hyena-for-spatial-inductive","title":"Multi-Dimensional Hyena for Spatial Inductive Bias","date":"2023-09-24","arxiv_id":"2309.13600","n_code_links":0,"syntology":null},{"paper":"/paper/weight-averaging-improves-knowledge","slug":"weight-averaging-improves-knowledge","title":"Weight Averaging Improves Knowledge Distillation under Domain Shift","date":"2023-09-20","arxiv_id":"2309.11446","n_code_links":1,"syntology":null},{"paper":"/paper/tuning-pre-trained-model-via-moment-probing","slug":"tuning-pre-trained-model-via-moment-probing","title":"Tuning Pre-trained Model via Moment Probing","date":"2023-07-21","arxiv_id":"2307.11342","n_code_links":1,"syntology":{"ran":8,"of":13,"n_ran_checked":2,"n_instrument":6,"unverified":5,"pointer_only":13,"phrase":"8 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; 6 where Syntology's instrument failed) · 5 unverified","official":{"repos":["mingzeg/moment-probing"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"domain-generalisation-with-bidirectional","title":"Domain Generalisation with Bidirectional Encoder Representations from Vision Transformers","date":"2023-07-16","arxiv_id":"2307.08117","n_code_links":0,"syntology":null},{"paper":"/paper/binaryvit-pushing-binary-vision-transformers","slug":"binaryvit-pushing-binary-vision-transformers","title":"BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models","date":"2023-06-29","arxiv_id":"2306.16678","n_code_links":1,"syntology":null},{"paper":null,"slug":"context-aware-attention-layers-coupled-with","title":"Context-aware attention layers coupled with optimal transport domain adaptation and multimodal fusion methods for recognizing dementia from spontaneous speech","date":"2023-05-25","arxiv_id":"2305.16406","n_code_links":0,"syntology":null},{"paper":null,"slug":"bi-vit-pushing-the-limit-of-vision","title":"Bi-ViT: Pushing the Limit of Vision Transformer Quantization","date":"2023-05-21","arxiv_id":"2305.12354","n_code_links":0,"syntology":null},{"paper":"/paper/what-makes-for-good-visual-tokenizers-for","slug":"what-makes-for-good-visual-tokenizers-for","title":"What Makes for Good Visual Tokenizers for Large Language Models?","date":"2023-05-20","arxiv_id":"2305.12223","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tencentarc/gvt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"instance-conditioned-gan-data-augmentation","title":"Instance-Conditioned GAN Data Augmentation for Representation Learning","date":"2023-03-16","arxiv_id":"2303.09677","n_code_links":0,"syntology":null},{"paper":"/paper/x-pruner-explainable-pruning-for-vision","slug":"x-pruner-explainable-pruning-for-vision","title":"X-Pruner: eXplainable Pruning for Vision Transformers","date":"2023-03-08","arxiv_id":"2303.04935","n_code_links":1,"syntology":null},{"paper":"/paper/a-fast-training-free-compression-framework","slug":"a-fast-training-free-compression-framework","title":"Training-Free Acceleration of ViTs with Delayed Spatial Merging","date":"2023-03-04","arxiv_id":"2303.02331","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-simple-recipe-for-competitive-low-compute","title":"A Simple Recipe for Competitive Low-compute Self supervised Vision Models","date":"2023-01-23","arxiv_id":"2301.09451","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-severity-of-diabetic-retinopathy","title":"Detecting Severity of Diabetic Retinopathy from Fundus Images: A Transformer Network-based Review","date":"2023-01-03","arxiv_id":"2301.00973","n_code_links":0,"syntology":null},{"paper":null,"slug":"dropkey-for-vision-transformer","title":"DropKey for Vision Transformer","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/improving-clip-fine-tuning-performance","slug":"improving-clip-fine-tuning-performance","title":"Improving CLIP Fine-tuning Performance","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/bort-towards-explainable-neural-networks-with","slug":"bort-towards-explainable-neural-networks-with","title":"Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint","date":"2022-12-18","arxiv_id":"2212.09062","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zbr17/bort"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-do-vision-transformers-learn-a-visual","slug":"what-do-vision-transformers-learn-a-visual","title":"What do Vision Transformers Learn? A Visual Exploration","date":"2022-12-13","arxiv_id":"2212.06727","n_code_links":1,"syntology":null},{"paper":"/paper/position-embedding-needs-an-independent-layer","slug":"position-embedding-needs-an-independent-layer","title":"Position Embedding Needs an Independent Layer Normalization","date":"2022-12-10","arxiv_id":"2212.05262","n_code_links":1,"syntology":null},{"paper":"/paper/noisyquant-noisy-bias-enhanced-post-training","slug":"noisyquant-noisy-bias-enhanced-post-training","title":"NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers","date":"2022-11-29","arxiv_id":"2211.16056","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kriskrisliu/NoisyQuant"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ss-cxr-multitask-representation-learning","slug":"ss-cxr-multitask-representation-learning","title":"SPCXR: Self-supervised Pretraining using Chest X-rays Towards a Domain Specific Foundation Model","date":"2022-11-23","arxiv_id":"2211.12944","n_code_links":0,"syntology":null},{"paper":"/paper/efficienttrain-exploring-generalized","slug":"efficienttrain-exploring-generalized","title":"EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones","date":"2022-11-17","arxiv_id":"2211.09703","n_code_links":1,"syntology":null},{"paper":"/paper/the-lottery-ticket-hypothesis-for-vision","slug":"the-lottery-ticket-hypothesis-for-vision","title":"Data Level Lottery Ticket Hypothesis for Vision Transformers","date":"2022-11-02","arxiv_id":"2211.01484","n_code_links":1,"syntology":null},{"paper":null,"slug":"ovit-an-accurate-second-order-pruning","title":"CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models","date":"2022-10-14","arxiv_id":"2210.09223","n_code_links":0,"syntology":null},{"paper":"/paper/q-vit-accurate-and-fully-quantized-low-bit","slug":"q-vit-accurate-and-fully-quantized-low-bit","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","date":"2022-10-13","arxiv_id":"2210.06707","n_code_links":1,"syntology":null},{"paper":"/paper/locality-guidance-for-improving-vision","slug":"locality-guidance-for-improving-vision","title":"Locality Guidance for Improving Vision Transformers on Tiny Datasets","date":"2022-07-20","arxiv_id":"2207.10026","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["lkhl/tiny-transformers"],"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":"lightweight-vision-transformer-with-cross","title":"Lightweight Vision Transformer with Cross Feature Attention","date":"2022-07-15","arxiv_id":"2207.07268","n_code_links":0,"syntology":null},{"paper":"/paper/robustifying-vision-transformer-without","slug":"robustifying-vision-transformer-without","title":"Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment","date":"2022-06-28","arxiv_id":"2206.13951","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kojima-takeshi188/cfa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sima-simple-softmax-free-attention-for-vision","slug":"sima-simple-softmax-free-attention-for-vision","title":"SimA: Simple Softmax-free Attention for Vision Transformers","date":"2022-06-17","arxiv_id":"2206.08898","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ucdvision/sima"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/sports-re-id-improving-re-identification-of","slug":"sports-re-id-improving-re-identification-of","title":"Sports Re-ID: Improving Re-Identification Of Players In Broadcast Videos Of Team Sports","date":"2022-06-06","arxiv_id":"2206.02373","n_code_links":1,"syntology":null},{"paper":"/paper/automated-progressive-learning-for-efficient","slug":"automated-progressive-learning-for-efficient","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","date":"2022-03-28","arxiv_id":"2203.14509","n_code_links":2,"syntology":{"ran":8,"of":13,"n_ran_checked":7,"n_instrument":1,"unverified":5,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["changlin31/autoprog"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/unified-visual-transformer-compression-1","slug":"unified-visual-transformer-compression-1","title":"Unified Visual Transformer Compression","date":"2022-03-15","arxiv_id":"2203.08243","n_code_links":1,"syntology":{"ran":9,"of":16,"n_ran_checked":6,"n_instrument":3,"unverified":7,"pointer_only":3,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["VITA-Group/UVC"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/the-principle-of-diversity-training-stronger","slug":"the-principle-of-diversity-training-stronger","title":"The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy","date":"2022-03-12","arxiv_id":"2203.06345","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["vita-group/diverse-vit"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/dit-self-supervised-pre-training-for-document","slug":"dit-self-supervised-pre-training-for-document","title":"DiT: Self-supervised Pre-training for Document Image Transformer","date":"2022-03-04","arxiv_id":"2203.02378","n_code_links":4,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/unilm"],"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/ensembles-of-vision-transformers-as-a-new","slug":"ensembles-of-vision-transformers-as-a-new","title":"Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology","date":"2022-03-03","arxiv_id":"2203.01726","n_code_links":1,"syntology":null},{"paper":"/paper/boat-bilateral-local-attention-vision","slug":"boat-bilateral-local-attention-vision","title":"BOAT: Bilateral Local Attention Vision Transformer","date":"2022-01-31","arxiv_id":"2201.13027","n_code_links":1,"syntology":null},{"paper":"/paper/a-comprehensive-study-of-image-classification","slug":"a-comprehensive-study-of-image-classification","title":"A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes","date":"2022-01-26","arxiv_id":"2201.10766","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mmoayeri/rival10"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tervit-an-efficient-ternary-vision","title":"TerViT: An Efficient Ternary Vision Transformer","date":"2022-01-20","arxiv_id":"2201.08050","n_code_links":0,"syntology":null},{"paper":"/paper/q-vit-fully-differentiable-quantization-for","slug":"q-vit-fully-differentiable-quantization-for","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","date":"2022-01-19","arxiv_id":"2201.07703","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":4,"n_instrument":3,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhexinli/Q-ViT-DeiT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-dimensional-model-compression-of-vision","slug":"multi-dimensional-model-compression-of-vision","title":"Multi-Dimensional Model Compression of Vision Transformer","date":"2021-12-31","arxiv_id":"2201.00043","n_code_links":1,"syntology":null},{"paper":"/paper/container-context-aggregation-networks","slug":"container-context-aggregation-networks","title":"Container: Context Aggregation Networks","date":"2021-12-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/searching-the-search-space-of-vision-1","slug":"searching-the-search-space-of-vision-1","title":"Searching the Search Space of Vision Transformer","date":"2021-11-29","arxiv_id":"2111.14725","n_code_links":2,"syntology":null},{"paper":"/paper/swat-spatial-structure-within-and-among","slug":"swat-spatial-structure-within-and-among","title":"SWAT: Spatial Structure Within and Among Tokens","date":"2021-11-26","arxiv_id":"2111.13677","n_code_links":1,"syntology":null},{"paper":"/paper/dbia-data-free-backdoor-injection-attack","slug":"dbia-data-free-backdoor-injection-attack","title":"DBIA: Data-free Backdoor Injection Attack against Transformer Networks","date":"2021-11-22","arxiv_id":"2111.11870","n_code_links":1,"syntology":null},{"paper":"/paper/nvit-vision-transformer-compression-and-1","slug":"nvit-vision-transformer-compression-and-1","title":"Global Vision Transformer Pruning with Hessian-Aware Saliency","date":"2021-10-10","arxiv_id":"2110.04869","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"token-pooling-in-visual-transformers","title":"Token Pooling in Vision Transformers","date":"2021-10-08","arxiv_id":"2110.03860","n_code_links":0,"syntology":null},{"paper":"/paper/mobilevit-light-weight-general-purpose-and","slug":"mobilevit-light-weight-general-purpose-and","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","date":"2021-10-05","arxiv_id":"2110.02178","n_code_links":31,"syntology":{"ran":53,"of":68,"n_ran_checked":44,"n_instrument":9,"unverified":15,"pointer_only":18,"phrase":"53 ran (of which 31 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 9 where Syntology's instrument failed) · 15 unverified","official":{"repos":["apple/ml-cvnets"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/mait-integrating-spatial-locality-into-image","slug":"mait-integrating-spatial-locality-into-image","title":"MaiT: integrating spatial locality into image transformers with attention masks","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/searching-for-efficient-multi-stage-vision","slug":"searching-for-efficient-multi-stage-vision","title":"Searching for Efficient Multi-Stage Vision Transformers","date":"2021-09-01","arxiv_id":"2109.00642","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-and-improving-mobile-level-vision","title":"Exploring and Improving Mobile Level Vision Transformers","date":"2021-08-30","arxiv_id":"2108.13015","n_code_links":0,"syntology":null},{"paper":null,"slug":"psvit-better-vision-transformer-via-token","title":"PSViT: Better Vision Transformer via Token Pooling and Attention Sharing","date":"2021-08-07","arxiv_id":"2108.03428","n_code_links":0,"syntology":null},{"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","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":0,"n_instrument":7,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","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"]}}},{"paper":null,"slug":"a-comparison-of-deep-learning-classification","title":"A Comparative Study of Deep Learning Classification Methods on a Small Environmental Microorganism Image Dataset (EMDS-6): from Convolutional Neural Networks to Visual Transformers","date":"2021-07-16","arxiv_id":"2107.07699","n_code_links":0,"syntology":null},{"paper":"/paper/cmt-convolutional-neural-networks-meet-vision","slug":"cmt-convolutional-neural-networks-meet-vision","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","date":"2021-07-13","arxiv_id":"2107.06263","n_code_links":14,"syntology":{"ran":4,"of":9,"n_ran_checked":3,"n_instrument":1,"unverified":5,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["ggjy/cmt.pytorch"],"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/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","n_code_links":2,"syntology":null},{"paper":"/paper/vision-transformer-architecture-search","slug":"vision-transformer-architecture-search","title":"ViTAS: Vision Transformer Architecture Search","date":"2021-06-25","arxiv_id":"2106.13700","n_code_links":1,"syntology":null},{"paper":"/paper/ia-red-2-interpretability-aware-redundancy","slug":"ia-red-2-interpretability-aware-redundancy","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","date":"2021-06-23","arxiv_id":"2106.12620","n_code_links":0,"syntology":null},{"paper":"/paper/solution-for-large-scale-long-tailed","slug":"solution-for-large-scale-long-tailed","title":"Solution for Large-scale Long-tailed Recognition with Noisy Labels","date":"2021-06-20","arxiv_id":"2106.10683","n_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","n_code_links":14,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","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"]}}},{"paper":"/paper/container-context-aggregation-network","slug":"container-context-aggregation-network","title":"Container: Context Aggregation Network","date":"2021-06-02","arxiv_id":"2106.01401","n_code_links":4,"syntology":{"ran":4,"of":7,"n_ran_checked":3,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["allenai/container","gaopengcuhk/Container"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"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","n_code_links":6,"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","n_code_links":21,"syntology":{"ran":9,"of":11,"n_ran_checked":6,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","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"]}}},{"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","n_code_links":15,"syntology":{"ran":17,"of":26,"n_ran_checked":17,"n_instrument":0,"unverified":9,"pointer_only":0,"phrase":"17 ran (of which 10 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 1 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","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"]}}},{"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","n_code_links":9,"syntology":null},{"paper":"/paper/transformer-in-transformer","slug":"transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","arxiv_id":"2103.00112","n_code_links":12,"syntology":{"ran":16,"of":24,"n_ran_checked":15,"n_instrument":1,"unverified":8,"pointer_only":5,"phrase":"16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","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"]}}},{"paper":"/paper/do-we-really-need-explicit-position-encodings","slug":"do-we-really-need-explicit-position-encodings","title":"Conditional Positional Encodings for Vision Transformers","date":"2021-02-22","arxiv_id":"2102.10882","n_code_links":2,"syntology":null},{"paper":"/paper/training-data-efficient-image-transformers","slug":"training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","arxiv_id":"2012.12877","n_code_links":40,"syntology":{"ran":12,"of":19,"n_ran_checked":9,"n_instrument":3,"unverified":7,"pointer_only":3,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","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"]}}}],"papers_shown":93,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":93,"with_a_code_link":60,"where_syntology_ran_a_sample":27,"not_listed_spam_title":0,"listed":93,"listed_where_code_ran":27,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":22,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":22,"listed_every_run_a_failure_of_syntologys_instrument":5,"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"},"papers_where_code_ran":27,"papers_where_code_ran_first_page":"/method/deit/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/deit/papers/ran/1","json":"/method/deit/papers/ran/1.json","rows":27}],"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":25},{"task":"/task/image-classification","name":"image-classification","papers":16},{"task":"/task/object-detection","name":"Object Detection","papers":11},{"task":"/task/quantization","name":"Quantization","papers":10},{"task":"/task/object-detection-1","name":"object-detection","papers":10},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":8},{"task":"/task/inductive-bias","name":"Inductive Bias","papers":6},{"task":null,"name":"Position","papers":5},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":5},{"task":"/task/efficient-vits","name":"Efficient ViTs","papers":4},{"task":"/task/fine-grained-image-classification","name":"Fine-Grained Image Classification","papers":4},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":4},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":3},{"task":"/task/document-image-classification","name":"Document Image Classification","papers":3},{"task":"/task/document-layout-analysis","name":"Document Layout Analysis","papers":3},{"task":"/task/mamba","name":"Mamba","papers":3},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":3},{"task":"/task/representation-learning","name":"Representation Learning","papers":3},{"task":"/task/all","name":"All","papers":2},{"task":"/task/automl","name":"AutoML","papers":2}],"tasks_shown":20,"n_tasks":78,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":27},{"year":"2022","papers":23},{"year":"2023","papers":20},{"year":"2024","papers":16},{"year":"2025","papers":6}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/deit"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=DeiT","read_at":"2026-10-05T00:54:42+00:00","query":"DeiT","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'DeiT' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["DeiT-LT"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"1be481095280ab442911e8bed84bbc2b331b89660e44a900d52f2eff688c6820","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}