{"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/locally-grouped-self-attention","slug":"locally-grouped-self-attention","name":"Locally-Grouped Self-Attention","full_name":"Locally-Grouped Self-Attention","full_name_withheld":false,"description_markdown":"**Locally-Grouped Self-Attention**, or **LSA**, is a local attention mechanism used in the [Twins-SVT](https://paperswithcode.com/method/twins-svt) architecture. Locally-grouped self-attention (LSA). Motivated by the group design in depthwise convolutions for efficient inference, we first equally divide the 2D feature maps into sub-windows, making self-attention communications only happen within each sub-window. This design also resonates with the multi-head design in self-attention, where the communications only occur within the channels of the same head. To be specific, the feature maps are divided into $m \\times n$ sub-windows. Without loss of generality, we assume $H \\% m=0$ and $W \\% n=0$. Each group contains $\\frac{H W}{m n}$ elements, and thus the computation cost of the self-attention in this window is $\\mathcal{O}\\left(\\frac{H^{2} W^{2}}{m^{2} n^{2}} d\\right)$, and the total cost is $\\mathcal{O}\\left(\\frac{H^{2} W^{2}}{m n} d\\right)$. If we let $k\\_{1}=\\frac{H}{n}$ and $k\\_{2}=\\frac{W}{n}$, the cost can be computed as $\\mathcal{O}\\left(k\\_{1} k\\_{2} H W d\\right)$, which is significantly more efficient when $k\\_{1} \\ll H$ and $k\\_{2} \\ll W$ and grows linearly with $H W$ if $k\\_{1}$ and $k\\_{2}$ are fixed.\r\n\r\nAlthough the locally-grouped self-attention mechanism is computation friendly, the image is divided into non-overlapping sub-windows. Thus, we need a mechanism to communicate between different sub-windows, as in Swin. Otherwise, the information would be limited to be processed locally, which makes the receptive field small and significantly degrades the performance as shown in our experiments. This resembles the fact that we cannot replace all standard convolutions by depth-wise convolutions in CNNs.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","paper":"/paper/twins-revisiting-spatial-attention-design-in","first_author":"Xiangxiang Chu","n_authors":8,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/twins-revisiting-spatial-attention-design-in"},"source":{"url":"https://arxiv.org/abs/2104.13840v4","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Attention Mechanisms","url":"/methods/category/attention-mechanisms","pwc_aliases":["attention-mechanisms-1"]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":null,"slug":"logically-at-factify-2023-a-multi-modal-fact","title":"Logically at Factify 2: A Multi-Modal Fact Checking System Based on Evidence Retrieval techniques and Transformer Encoder Architecture","date":"2023-01-09","arxiv_id":"2301.03127","n_code_links":0,"syntology":null},{"paper":"/paper/twins-revisiting-spatial-attention-design-in","slug":"twins-revisiting-spatial-attention-design-in","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","date":"2021-04-28","arxiv_id":"2104.13840","n_code_links":9,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Meituan-AutoML/Twins"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}],"papers_shown":2,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":2,"with_a_code_link":1,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":1,"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":1,"papers_where_code_ran_first_page":"/method/locally-grouped-self-attention/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/locally-grouped-self-attention/papers/ran/1","json":"/method/locally-grouped-self-attention/papers/ran/1.json","rows":1}],"tasks":[{"task":null,"name":"Avg","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/fact-checking","name":"Fact Checking","papers":1},{"task":"/task/fact-verification","name":"Fact Verification","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2021","papers":1},{"year":"2023","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/locally-grouped-self-attention"},"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=Locally-Grouped%20Self-Attention","read_at":"2026-10-05T00:58:41+00:00","query":"Locally-Grouped Self-Attention","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":"2104.13840","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 'Locally-Grouped Self-Attention' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Grouped Self-Attention (GSA)","Grouped Head Attention","Omni Self-Attention (OSA)","self-modulating attention","Orthogonal Self-Attention","Local Self-Attention Block","Self-Gating Attention (SGA)","Hierarchical Self-Attention"],"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":"3c7c2bdd44eedca0d231d35941321af2ce1b4f1f9813866c4befc368c45cf170","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}