{"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/rethinking-semantic-segmentation-from-a","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","arxiv_id":"2012.15840","date":"2020-12-31","proceeding":"CVPR 2021 1","authors":["Sixiao Zheng","Jiachen Lu","Hengshuang Zhao","Xiatian Zhu","Zekun Luo","Yabiao Wang","Yanwei Fu","Jianfeng Feng","Tao Xiang","Philip H. S. Torr","Li Zhang"],"abstract":"Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (ie, without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE20K test server leaderboard on the day of submission.","url_abs":"https://arxiv.org/abs/2012.15840v3","url_pdf":"https://arxiv.org/pdf/2012.15840v3.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":"rethinking-semantic-segmentation-from-a","repo_url":"https://github.com/fudan-zvg/SETR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-semantic-segmentation-from-a","repo_url":"https://github.com/920232796/setr-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-semantic-segmentation-from-a","repo_url":"https://github.com/gupta-abhay/setr-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-semantic-segmentation-from-a","repo_url":"https://github.com/BR-IDL/PaddleViT/tree/main/semantic_segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"rethinking-semantic-segmentation-from-a","repo_url":"https://github.com/PaddlePaddle/PaddleSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"setr","method_name":"SETR"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/medical-image-segmentation-on-synapse-multi","task":"Medical Image Segmentation","dataset":"Synapse multi-organ CT","model":"SETR","rank_in_archive_order":20,"of":23,"metrics":{"Avg DSC":"79.60"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"SETR-MLA (160k, MS)","rank_in_archive_order":116,"of":235,"metrics":{"Validation mIoU":"50.28"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"SETR-PUP++","rank_in_archive_order":37,"of":105,"metrics":{"Mean IoU (class)":"81.64%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"SETR-PUP (80k, MS)","rank_in_archive_order":37,"of":99,"metrics":{"mIoU":"82.15"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-dada-seg","task":"Semantic Segmentation","dataset":"DADA-seg","model":"SETR (PUP, Transformer-Large)","rank_in_archive_order":4,"of":28,"metrics":{"mIoU":"31.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-dada-seg","task":"Semantic Segmentation","dataset":"DADA-seg","model":"SETR (MLA, Transformer-Large)","rank_in_archive_order":5,"of":28,"metrics":{"mIoU":"30.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-densepass","task":"Semantic Segmentation","dataset":"DensePASS","model":"SETR (PUP, Transformer-L)","rank_in_archive_order":18,"of":36,"metrics":{"mIoU":"35.7%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-densepass","task":"Semantic Segmentation","dataset":"DensePASS","model":"SETR (MLA, Transformer-L)","rank_in_archive_order":19,"of":36,"metrics":{"mIoU":"35.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-foodseg103","task":"Semantic Segmentation","dataset":"FoodSeg103","model":"SeTR-MLA (ViT-16/B)","rank_in_archive_order":2,"of":7,"metrics":{"mIoU":"45.1"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-foodseg103","task":"Semantic Segmentation","dataset":"FoodSeg103","model":"SeTR-Naive (ViT-16/B)","rank_in_archive_order":5,"of":7,"metrics":{"mIoU":"41.3"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-pascal-context","task":"Semantic Segmentation","dataset":"PASCAL Context","model":"SETR-MLA (16, 80k, MS)","rank_in_archive_order":27,"of":66,"metrics":{"mIoU":"55.83"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-urbanlf","task":"Semantic Segmentation","dataset":"UrbanLF","model":"SETR (ViT-Large)","rank_in_archive_order":9,"of":14,"metrics":{"mIoU (Real)":"77.74","mIoU (Syn)":"77.69"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.15840","atlas_url":"https://app.syntology.ai/?focus=2012.15840","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":"2012.15840"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.15840\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.15840"},"call":"get_concepts_for_paper(arxiv_id=\"2012.15840\")"}],"by_repo":[{"repo":"fudan-zvg/SETR","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"920232796/setr-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"gupta-abhay/setr-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"BR-IDL/PaddleViT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PaddlePaddle/PaddleSeg","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2109.09406"],"harvested_for_calls":[{"arxiv_id":"2109.09406","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2109.09406"},"call":"get_harvested_code_for_paper(arxiv_id=\"2109.09406\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"912de2a9cecd0c89a9210d8076bd7af3b206621a949086ec3c9ba4ae5432a334","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}