{"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":"/paper/patch-slimming-for-efficient-vision","title":"Patch Slimming for Efficient Vision Transformers","arxiv_id":"2106.02852","date":"2021-06-05","proceeding":"CVPR 2022 1","authors":["Yehui Tang","Kai Han","Yunhe Wang","Chang Xu","Jianyuan Guo","Chao Xu","DaCheng Tao"],"abstract":"This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series of computer vision tasks. However, similar to that of convolutional neural networks, the huge computational cost of vision transformers is still a severe issue. Considering that the attention mechanism aggregates different patches layer-by-layer, we present a novel patch slimming approach that discards useless patches in a top-down paradigm. We first identify the effective patches in the last layer and then use them to guide the patch selection process of previous layers. For each layer, the impact of a patch on the final output feature is approximated and patches with less impact will be removed. Experimental results on benchmark datasets demonstrate that the proposed method can significantly reduce the computational costs of vision transformers without affecting their performances. For example, over 45% FLOPs of the ViT-Ti model can be reduced with only 0.2% top-1 accuracy drop on the ImageNet dataset.","url_abs":"https://arxiv.org/abs/2106.02852v2","url_pdf":"https://arxiv.org/pdf/2106.02852v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"efficient-vits","task_name":"Efficient ViTs"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-lv-vit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (With LV-ViT-S)","model":"DPS-LV-ViT-S","rank_in_archive_order":12,"of":19,"metrics":{"GFLOPs":"4.5","Top 1 Accuracy":"82.9"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-lv-vit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (With LV-ViT-S)","model":"PS-LV-ViT-S","rank_in_archive_order":18,"of":19,"metrics":{"GFLOPs":"4.7","Top 1 Accuracy":"82.4"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-S)","model":"DPS-ViT","rank_in_archive_order":20,"of":41,"metrics":{"GFLOPs":"2.4","Top 1 Accuracy":"79.5"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-S)","model":"PS-ViT","rank_in_archive_order":22,"of":41,"metrics":{"GFLOPs":"2.6","Top 1 Accuracy":"79.4"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-t","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-T)","model":"DPS-ViT","rank_in_archive_order":8,"of":22,"metrics":{"GFLOPs":"0.6","Top 1 Accuracy":"72.1"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-t","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-T)","model":"PS-ViT","rank_in_archive_order":11,"of":22,"metrics":{"GFLOPs":"0.7","Top 1 Accuracy":"72.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.02852","atlas_url":"https://app.syntology.ai/?focus=2106.02852","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2106.02852"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2106.02852\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2106.02852"},"call":"get_concepts_for_paper(arxiv_id=\"2106.02852\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"402ace404d09e642a046a31a91c067ca0dac373f53c3c55bb9e5fdd0591cec1b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}