{"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/focal-transformers","slug":"focal-transformers","name":"Focal Transformers","full_name":"Focal Transformers","full_name_withheld":false,"description_markdown":"The **focal self-attention** is built to make Transformer layers scalable to high-resolution inputs.  Instead of attending all tokens at fine-grain, the approach attends the fine-grain tokens only locally, but the summarized ones globally. As such, it can cover as many regions as standard self-attention but with much less cost. An image is first partitioned into patches, resulting in visual tokens. Then a patch embedding layer, consisting of a convolutional layer with filter and stride of same size, to project the patches into hidden features. This spatial feature map in then passed to four stages of focal Transformer blocks. Each focal Transformer block consists of $N_i$ focal Transformer layers. Patch embedding layers are used in between to reduce spatial size of feature map by factor 2, while feature dimension increased by 2.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","paper":"/paper/focal-self-attention-for-local-global","first_author":"Jianwei Yang","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/focal-self-attention-for-local-global"},"source":{"url":"https://arxiv.org/abs/2107.00641v1","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Vision Transformers","url":"/methods/category/vision-transformers","pwc_aliases":["vision-transformer"]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":"/paper/explicitly-increasing-input-information","slug":"explicitly-increasing-input-information","title":"Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets","date":"2022-10-25","arxiv_id":"2210.14319","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":2,"n_instrument":2,"unverified":3,"pointer_only":7,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["xiangyu8/densevt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/focal-wnet-an-architecture-unifying","slug":"focal-wnet-an-architecture-unifying","title":"Focal-WNet: An Architecture Unifying Convolution and Attention for Depth Estimation","date":"2022-07-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/focal-attention-for-long-range-interactions","slug":"focal-attention-for-long-range-interactions","title":"Focal Attention for Long-Range Interactions in Vision Transformers","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/focal-self-attention-for-local-global","slug":"focal-self-attention-for-local-global","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","date":"2021-07-01","arxiv_id":"2107.00641","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["microsoft/Focal-Transformer"],"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","unlocated"]}}}],"papers_shown":4,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":4,"with_a_code_link":4,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":4,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":1,"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":2,"papers_where_code_ran_first_page":"/method/focal-transformers/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/focal-transformers/papers/ran/1","json":"/method/focal-transformers/papers/ran/1.json","rows":2}],"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/image-classification","name":"image-classification","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":1},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":1},{"task":"/task/monocular-depth-estimation","name":"Monocular Depth Estimation","papers":1}],"tasks_shown":9,"n_tasks":9,"usage_by_year":[{"year":"2021","papers":2},{"year":"2022","papers":2}],"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/focal-transformers"},"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=Focal%20Transformers","read_at":"2026-10-05T00:56:06+00:00","query":"Focal Transformers","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":"2107.00641","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 'Focal Transformers' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["FoCal","FOCAL","RL-Focal","CKA-focal","Focal Reward","Focal Guidance","Anti-Focal loss","Focal Rewriting"],"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":"b9be6ca20550a0ba7e7a8648fa57be189964ad2ef7db4575ffae6eba606bd145","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}