{"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/beyond-attentive-tokens-incorporating-token","title":"Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers","arxiv_id":"2211.11315","date":"2022-11-21","proceeding":"CVPR 2023 1","authors":["Sifan Long","Zhen Zhao","Jimin Pi","Shengsheng Wang","Jingdong Wang"],"abstract":"Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Many pruning methods have been proposed to remove redundant tokens for efficient vision transformers recently. However, existing studies mainly focus on the token importance to preserve local attentive tokens but completely ignore the global token diversity. In this paper, we emphasize the cruciality of diverse global semantics and propose an efficient token decoupling and merging method that can jointly consider the token importance and diversity for token pruning. According to the class token attention, we decouple the attentive and inattentive tokens. In addition to preserving the most discriminative local tokens, we merge similar inattentive tokens and match homogeneous attentive tokens to maximize the token diversity. Despite its simplicity, our method obtains a promising trade-off between model complexity and classification accuracy. On DeiT-S, our method reduces the FLOPs by 35% with only a 0.2% accuracy drop. Notably, benefiting from maintaining the token diversity, our method can even improve the accuracy of DeiT-T by 0.1% after reducing its FLOPs by 40%.","url_abs":"https://arxiv.org/abs/2211.11315v1","url_pdf":"https://arxiv.org/pdf/2211.11315v1.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":[{"paper_slug":"beyond-attentive-tokens-incorporating-token","repo_url":"https://github.com/BWLONG/BeyondAttentiveTokens","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"efficient-vits","task_name":"Efficient ViTs"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"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":"BAT","rank_in_archive_order":6,"of":19,"metrics":{"GFLOPs":"4.7","Top 1 Accuracy":"83.1"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-S)","model":"BAT (70%)","rank_in_archive_order":16,"of":41,"metrics":{"GFLOPs":"3.0","Top 1 Accuracy":"79.6"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-S)","model":"BAT (60%)","rank_in_archive_order":26,"of":41,"metrics":{"GFLOPs":"2.6","Top 1 Accuracy":"79.3"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-S)","model":"BAT (50%)","rank_in_archive_order":31,"of":41,"metrics":{"GFLOPs":"2.3","Top 1 Accuracy":"79.0"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-S)","model":"BAT (40%)","rank_in_archive_order":34,"of":41,"metrics":{"GFLOPs":"2.0","Top 1 Accuracy":"78.6"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-S)","model":"BAT (30%)","rank_in_archive_order":40,"of":41,"metrics":{"GFLOPs":"1.8","Top 1 Accuracy":"77.8"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-S)","model":"BAT (20%)","rank_in_archive_order":41,"of":41,"metrics":{"GFLOPs":"1.6","Top 1 Accuracy":"76.4"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-t","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-T)","model":"BAT","rank_in_archive_order":4,"of":22,"metrics":{"GFLOPs":"0.8","Top 1 Accuracy":"72.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.11315","atlas_url":"https://app.syntology.ai/?focus=2211.11315","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":"2211.11315"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2211.11315\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2211.11315"},"call":"get_concepts_for_paper(arxiv_id=\"2211.11315\")"}],"by_repo":[{"repo":"BWLONG/BeyondAttentiveTokens","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7da523949054efd7cb775c91510bda54f628cd08bfdf0c5387220c67a020de06","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}