{"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/locally-enhanced-self-attention-rethinking","title":"Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context Terms","arxiv_id":"2107.05637","date":"2021-07-12","proceeding":null,"authors":["Chenglin Yang","Siyuan Qiao","Adam Kortylewski","Alan Yuille"],"abstract":"Self-Attention has become prevalent in computer vision models. Inspired by fully connected Conditional Random Fields (CRFs), we decompose self-attention into local and context terms. They correspond to the unary and binary terms in CRF and are implemented by attention mechanisms with projection matrices. We observe that the unary terms only make small contributions to the outputs, and meanwhile standard CNNs that rely solely on the unary terms achieve great performances on a variety of tasks. Therefore, we propose Locally Enhanced Self-Attention (LESA), which enhances the unary term by incorporating it with convolutions, and utilizes a fusion module to dynamically couple the unary and binary operations. In our experiments, we replace the self-attention modules with LESA. The results on ImageNet and COCO show the superiority of LESA over convolution and self-attention baselines for the tasks of image recognition, object detection, and instance segmentation. The code is made publicly available.","url_abs":"https://arxiv.org/abs/2107.05637v3","url_pdf":"https://arxiv.org/pdf/2107.05637v3.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":"locally-enhanced-self-attention-rethinking","repo_url":"https://github.com/Chenglin-Yang/LESA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"locally-enhanced-self-attention-rethinking","repo_url":"https://github.com/Chenglin-Yang/LESA_classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"locally-enhanced-self-attention-rethinking","repo_url":"https://github.com/Chenglin-Yang/LESA_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"crf","method_name":"CRF"},{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.05637","atlas_url":"https://app.syntology.ai/?focus=2107.05637","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":"2107.05637"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2107.05637\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2107.05637"},"call":"get_concepts_for_paper(arxiv_id=\"2107.05637\")"}],"by_repo":[{"repo":"Chenglin-Yang/LESA","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Chenglin-Yang/LESA_classification","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Chenglin-Yang/LESA_detection","kind":"listed","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":"7b65848d2b6592c0b0001d24fedc0405a63cb02478c7523f74c637649e4a6205","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}