{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/semantic-flow-for-fast-and-accurate-scene","title":"Semantic Flow for Fast and Accurate Scene Parsing","arxiv_id":"2002.10120","date":"2020-02-24","proceeding":"ECCV 2020 8","authors":["Xiangtai Li","Ansheng You","Zhen Zhu","Houlong Zhao","Maoke Yang","Kuiyuan Yang","Yunhai Tong"],"abstract":"In this paper, we focus on designing effective method for fast and accurate scene parsing. A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation. Two strategies are widely used -- atrous convolutions and feature pyramid fusion, are either computation intensive or ineffective. Inspired by the Optical Flow for motion alignment between adjacent video frames, we propose a Flow Alignment Module (FAM) to learn Semantic Flow between feature maps of adjacent levels, and broadcast high-level features to high resolution features effectively and efficiently. Furthermore, integrating our module to a common feature pyramid structure exhibits superior performance over other real-time methods even on light-weight backbone networks, such as ResNet-18. Extensive experiments are conducted on several challenging datasets, including Cityscapes, PASCAL Context, ADE20K and CamVid. Especially, our network is the first to achieve 80.4\\% mIoU on Cityscapes with a frame rate of 26 FPS. The code is available at \\url{https://github.com/lxtGH/SFSegNets}.","url_abs":"https://arxiv.org/abs/2002.10120v3","url_pdf":"https://arxiv.org/pdf/2002.10120v3.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":"semantic-flow-for-fast-and-accurate-scene","repo_url":"https://github.com/donnyyou/torchcv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"semantic-flow-for-fast-and-accurate-scene","repo_url":"https://github.com/lxtGH/SFSegNets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"semantic-flow-for-fast-and-accurate-scene","repo_url":"https://github.com/MaybeShewill-CV/sfnet-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"semantic-flow-for-fast-and-accurate-scene","repo_url":"https://github.com/Shualite/SFNet.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"semantic-flow-for-fast-and-accurate-scene","repo_url":"https://github.com/sithu31296/semantic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"semantic-flow-for-fast-and-accurate-scene","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":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"real-time-semantic-segmentation","task_name":"Real-Time Semantic Segmentation"},{"task_slug":"scene-parsing","task_name":"Scene Parsing"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"flow-alignment-module","method_name":"Flow Alignment Module"}],"datasets_introduced":[],"methods_introduced":[{"slug":"flow-alignment-module","name":"Flow Alignment Module","full_name":"Flow Alignment Module"}],"results":[{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes test","model":"SFNet-R18","rank_in_archive_order":2,"of":39,"metrics":{"Frame (fps)":"25.7(1080Ti)","Time (ms)":"39.2","mIoU":"80.4%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-bdd100k-val","task":"Semantic Segmentation","dataset":"BDD100K val","model":"SFNet(DF2)","rank_in_archive_order":19,"of":24,"metrics":{"mIoU":"60.2(208FPS 4090)"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-bdd100k-val","task":"Semantic Segmentation","dataset":"BDD100K val","model":"SFNet(DF1)","rank_in_archive_order":20,"of":24,"metrics":{"mIoU":"55.4(70.3fps)"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-bdd100k-val","task":"Semantic Segmentation","dataset":"BDD100K val","model":"SFNet(ResNet-18)","rank_in_archive_order":21,"of":24,"metrics":{"mIoU":"60.6(132.5FPS 4090)"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.10120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10120"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/donnyyou/torchcv","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleSeg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lxtGH/SFSegNets","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaybeShewill-CV/sfnet-tensorflow","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Shualite/SFNet.pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sithu31296/semantic-segmentation","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1},"listed":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"4a6bd97bd6bba0ad","entry":"assert_tensor_type","repo":"donnyyou/torchcv","repo_kind":"official","path":"lib/parallel/data_container.py","file_url":"https://github.com/donnyyou/torchcv/blob/HEAD/lib/parallel/data_container.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4a6bd97bd6bba0ad"}},{"code_sha256_prefix":"72b89f53f5854825","entry":"get_input_device","repo":"donnyyou/torchcv","repo_kind":"official","path":"lib/parallel/_functions.py","file_url":"https://github.com/donnyyou/torchcv/blob/HEAD/lib/parallel/_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"72b89f53f5854825"}},{"code_sha256_prefix":"aa73f0787179b863","entry":"scatter","repo":"donnyyou/torchcv","repo_kind":"official","path":"lib/parallel/_functions.py","file_url":"https://github.com/donnyyou/torchcv/blob/HEAD/lib/parallel/_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa73f0787179b863"}},{"code_sha256_prefix":"12610892f9cebded","entry":"scatter","repo":"donnyyou/torchcv","repo_kind":"official","path":"lib/parallel/scatter_gather.py","file_url":"https://github.com/donnyyou/torchcv/blob/HEAD/lib/parallel/scatter_gather.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12610892f9cebded"}},{"code_sha256_prefix":"ea53ec023a304e67","entry":"scatter_kwargs","repo":"donnyyou/torchcv","repo_kind":"official","path":"lib/parallel/scatter_gather.py","file_url":"https://github.com/donnyyou/torchcv/blob/HEAD/lib/parallel/scatter_gather.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea53ec023a304e67"}},{"code_sha256_prefix":"1b772e24adfd25a7","entry":"sf_resnet18","repo":"Shualite/SFNet.pytorch","repo_kind":"listed","path":"sfnet/sfnet.py","file_url":"https://github.com/Shualite/SFNet.pytorch/blob/HEAD/sfnet/sfnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b772e24adfd25a7"}},{"code_sha256_prefix":"b749652595868268","entry":"sf_resnet34","repo":"Shualite/SFNet.pytorch","repo_kind":"listed","path":"sfnet/sfnet.py","file_url":"https://github.com/Shualite/SFNet.pytorch/blob/HEAD/sfnet/sfnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b749652595868268"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}