{"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/temporally-distributed-networks-for-fast","title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","arxiv_id":"2004.01800","date":"2020-04-03","proceeding":"CVPR 2020 6","authors":["Ping Hu","Fabian Caba Heilbron","Oliver Wang","Zhe Lin","Stan Sclaroff","Federico Perazzi"],"abstract":"We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation. We observe that features extracted from a certain high-level layer of a deep CNN can be approximated by composing features extracted from several shallower sub-networks. Leveraging the inherent temporal continuity in videos, we distribute these sub-networks over sequential frames. Therefore, at each time step, we only need to perform a lightweight computation to extract a sub-features group from a single sub-network. The full features used for segmentation are then recomposed by application of a novel attention propagation module that compensates for geometry deformation between frames. A grouped knowledge distillation loss is also introduced to further improve the representation power at both full and sub-feature levels. Experiments on Cityscapes, CamVid, and NYUD-v2 demonstrate that our method achieves state-of-the-art accuracy with significantly faster speed and lower latency.","url_abs":"https://arxiv.org/abs/2004.01800v2","url_pdf":"https://arxiv.org/pdf/2004.01800v2.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":"temporally-distributed-networks-for-fast","repo_url":"https://github.com/feinanshan/TDNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"real-time-semantic-segmentation","task_name":"Real-Time Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/real-time-semantic-segmentation-on-camvid","task":"Real-Time Semantic Segmentation","dataset":"CamVid","model":"TD2-PSP50","rank_in_archive_order":11,"of":29,"metrics":{"Frame (fps)":"11(TitanX)","Time (ms)":"90","mIoU":"76.0"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-camvid","task":"Real-Time Semantic Segmentation","dataset":"CamVid","model":"TD4-PSP18","rank_in_archive_order":18,"of":29,"metrics":{"Frame (fps)":"25(TitanX)","Time (ms)":"40","mIoU":"72.6"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes test","model":"TD4-BISE18","rank_in_archive_order":15,"of":39,"metrics":{"Frame (fps)":"47.6 (Titan X)","Time (ms)":"21","mIoU":"74.9%"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-nyu-depth-1","task":"Real-Time Semantic Segmentation","dataset":"NYU Depth v2","model":"TD2-PSP50","rank_in_archive_order":4,"of":10,"metrics":{"Speed(ms/f)":"35","mIoU":"43.5"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-nyu-depth-1","task":"Real-Time Semantic Segmentation","dataset":"NYU Depth v2","model":"TD4-PSP18","rank_in_archive_order":9,"of":10,"metrics":{"Speed(ms/f)":"19","mIoU":"37.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"TD2-PSP50","rank_in_archive_order":100,"of":121,"metrics":{"Mean IoU":"43.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"TD4-PSP18","rank_in_archive_order":113,"of":121,"metrics":{"Mean IoU":"37.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-urbanlf","task":"Semantic Segmentation","dataset":"UrbanLF","model":"TDNet (ResNet-50)","rank_in_archive_order":12,"of":14,"metrics":{"mIoU (Real)":"76.48","mIoU (Syn)":"74.71"},"uses_additional_data":false},{"leaderboard":"/sota/video-semantic-segmentation-on-camvid","task":"Video Semantic Segmentation","dataset":"CamVid","model":"TDNet-50","rank_in_archive_order":3,"of":6,"metrics":{"Mean IoU":"76.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-semantic-segmentation-on-cityscapes-val","task":"Video Semantic Segmentation","dataset":"Cityscapes val","model":"TDNet-50 [9]","rank_in_archive_order":2,"of":9,"metrics":{"mIoU":"79.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2004.01800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01800"}},"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/feinanshan/TDNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":3},"by_repo_kind":{"listed":{"samples":5,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"feinanshan/TDNet","repo_kind":"listed","path":"Testing/model/pspnet/resnet.py","file_url":"https://github.com/feinanshan/TDNet/blob/HEAD/Testing/model/pspnet/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"f1e67bfcea91df50","entry":"recursive_glob","repo":"feinanshan/TDNet","repo_kind":"listed","path":"Training/ptsemseg/utils.py","file_url":"https://github.com/feinanshan/TDNet/blob/HEAD/Training/ptsemseg/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1e67bfcea91df50"}},{"code_sha256_prefix":"3a8e7e1d2e1dc425","entry":"alpha_blend","repo":"feinanshan/TDNet","repo_kind":"listed","path":"Training/ptsemseg/utils.py","file_url":"https://github.com/feinanshan/TDNet/blob/HEAD/Training/ptsemseg/utils.py","link_basis":"harvester_set","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":"3a8e7e1d2e1dc425"}},{"code_sha256_prefix":"513d282e7c3d723b","entry":"recursive_glob","repo":"feinanshan/TDNet","repo_kind":"listed","path":"Testing/dataloader.py","file_url":"https://github.com/feinanshan/TDNet/blob/HEAD/Testing/dataloader.py","link_basis":"harvester_set","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":"513d282e7c3d723b"}},{"code_sha256_prefix":"acc7d485dfe2d3b1","entry":"split_fanet_dict","repo":"feinanshan/TDNet","repo_kind":"listed","path":"Training/ptsemseg/utils.py","file_url":"https://github.com/feinanshan/TDNet/blob/HEAD/Training/ptsemseg/utils.py","link_basis":"harvester_set","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":"acc7d485dfe2d3b1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}