{"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/fast-searching-for-a-faster-arbitrarily","title":"FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation","arxiv_id":"2111.02394","date":"2021-11-03","proceeding":null,"authors":["Zhe Chen","Jiahao Wang","Wenhai Wang","Guo Chen","Enze Xie","Ping Luo","Tong Lu"],"abstract":"We propose an accurate and efficient scene text detection framework, termed FAST (i.e., faster arbitrarily-shaped text detector). Different from recent advanced text detectors that used complicated post-processing and hand-crafted network architectures, resulting in low inference speed, FAST has two new designs. (1) We design a minimalist kernel representation (only has 1-channel output) to model text with arbitrary shape, as well as a GPU-parallel post-processing to efficiently assemble text lines with a negligible time overhead. (2) We search the network architecture tailored for text detection, leading to more powerful features than most networks that are searched for image classification. Benefiting from these two designs, FAST achieves an excellent trade-off between accuracy and efficiency on several challenging datasets, including Total Text, CTW1500, ICDAR 2015, and MSRA-TD500. For example, FAST-T yields 81.6% F-measure at 152 FPS on Total-Text, outperforming the previous fastest method by 1.7 points and 70 FPS in terms of accuracy and speed. With TensorRT optimization, the inference speed can be further accelerated to over 600 FPS. Code and models will be released at https://github.com/czczup/FAST.","url_abs":"https://arxiv.org/abs/2111.02394v2","url_pdf":"https://arxiv.org/pdf/2111.02394v2.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":"fast-searching-for-a-faster-arbitrarily","repo_url":"https://github.com/czczup/FAST","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fast-searching-for-a-faster-arbitrarily","repo_url":"https://github.com/whai362/pan_pp.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"text-detection","task_name":"Text Detection"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"FAST-B-1280","rank_in_archive_order":16,"of":43,"metrics":{"F-Measure":"87.1","FPS":"15.7","Precision":"89.7","Recall":"84.6"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"FAST-B-896","rank_in_archive_order":20,"of":43,"metrics":{"F-Measure":"86.3","FPS":"31.8","Precision":"89.2","Recall":"83.6"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"FAST-B-736","rank_in_archive_order":24,"of":43,"metrics":{"F-Measure":"84.7","FPS":"42.7","Precision":"88.0","Recall":"81.7"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"FAST-S-736","rank_in_archive_order":32,"of":43,"metrics":{"F-Measure":"82.9","FPS":"53.9","Precision":"86.3","Recall":"79.8"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"FAST-T-736","rank_in_archive_order":35,"of":43,"metrics":{"F-Measure":"81.7","FPS":"60.9","Precision":"86","Recall":"77.9"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-msra-td500","task":"Scene Text Detection","dataset":"MSRA-TD500","model":"FAST-B-736","rank_in_archive_order":2,"of":18,"metrics":{"F-Measure":"87.3","FPS":"56.8","Precision":"92.1","Recall":"83"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-msra-td500","task":"Scene Text Detection","dataset":"MSRA-TD500","model":"FAST-S-736","rank_in_archive_order":4,"of":18,"metrics":{"F-Measure":"86.4","FPS":"72","Precision":"91.6","Recall":"81.7"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-msra-td500","task":"Scene Text Detection","dataset":"MSRA-TD500","model":"FAST-T-736","rank_in_archive_order":7,"of":18,"metrics":{"F-Measure":"84.9","FPS":"79.6","Precision":"88.1","Recall":"81.9"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-msra-td500","task":"Scene Text Detection","dataset":"MSRA-TD500","model":"FAST-T-512","rank_in_archive_order":8,"of":18,"metrics":{"F-Measure":"84.5","FPS":"137.2","Precision":"91.1","Recall":"78.8"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-scut-ctw1500","task":"Scene Text Detection","dataset":"SCUT-CTW1500","model":"FAST-B-640","rank_in_archive_order":7,"of":17,"metrics":{"F-Measure":"84.2","FPS":"66.5","Precision":"87.8","Recall":"80.9"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-scut-ctw1500","task":"Scene Text Detection","dataset":"SCUT-CTW1500","model":"FAST-B-512","rank_in_archive_order":11,"of":17,"metrics":{"F-Measure":"82.9","FPS":"92.6","Precision":"85.7","Recall":"80.2"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-scut-ctw1500","task":"Scene Text Detection","dataset":"SCUT-CTW1500","model":"FAST-S-512","rank_in_archive_order":13,"of":17,"metrics":{"F-Measure":"82","FPS":"112.9","Precision":"85.6","Recall":"78.7"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-scut-ctw1500","task":"Scene Text Detection","dataset":"SCUT-CTW1500","model":"FAST-T-512","rank_in_archive_order":14,"of":17,"metrics":{"F-Measure":"81.5","FPS":"129.1","Precision":"85.5","Recall":"77.9"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-total-text","task":"Scene Text Detection","dataset":"Total-Text","model":"FAST-B-800","rank_in_archive_order":4,"of":27,"metrics":{"F-Measure":"87.5%","FPS":"46","Precision":"90.0","Recall":"85.2"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-total-text","task":"Scene Text Detection","dataset":"Total-Text","model":"FAST-B-640","rank_in_archive_order":8,"of":27,"metrics":{"F-Measure":"86.4%","FPS":"67.5","Precision":"89.9","Recall":"83.2"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-total-text","task":"Scene Text Detection","dataset":"Total-Text","model":"FAST-B-512","rank_in_archive_order":10,"of":27,"metrics":{"F-Measure":"85.8%","FPS":"93.2","Precision":"89.6","Recall":"82.4"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-total-text","task":"Scene Text Detection","dataset":"Total-Text","model":"FAST-S-512","rank_in_archive_order":14,"of":27,"metrics":{"F-Measure":"84.9%","FPS":"115.5","Precision":"88.3","Recall":"81.7"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-total-text","task":"Scene Text Detection","dataset":"Total-Text","model":"FAST-T-448","rank_in_archive_order":20,"of":27,"metrics":{"F-Measure":"81.6%","FPS":"152.8","Precision":"86.5","Recall":"77.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"czczup/FAST","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"whai362/pan_pp.pytorch","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":"fbe29666e6c88b4c4ad97c46a2764557592b5bd1acdab7723adfaf0bed6b4d0a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}