{"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/efficient-semantic-video-segmentation-with","title":"Efficient Semantic Video Segmentation with Per-frame Inference","arxiv_id":"2002.11433","date":"2020-02-26","proceeding":"ECCV 2020 8","authors":["Yifan Liu","Chunhua Shen","Changqian Yu","Jingdong Wang"],"abstract":"For semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence. Advanced methods take into considerations the correlations in the video sequence, e.g., by propagating the results to the neighboring frames using optical flow, or extracting the frame representations with other frames, which may lead to inaccurate results or unbalanced latency. In this work, we process efficient semantic video segmentation in a per-frame fashion during the inference process. Different from previous per-frame models, we explicitly consider the temporal consistency among frames as extra constraints during the training process and embed the temporal consistency into the segmentation network. Therefore, in the inference process, we can process each frame independently with no latency, and improve the temporal consistency with no extra computational cost and post-processing. We employ compact models for real-time execution. To narrow the performance gap between compact models and large models, new knowledge distillation methods are designed. Our results outperform previous keyframe based methods with a better trade-off between the accuracy and the inference speed on popular benchmarks, including the Cityscapes and Camvid. The temporal consistency is also improved compared with corresponding baselines which are trained with each frame independently. Code is available at: https://tinyurl.com/segment-video","url_abs":"https://arxiv.org/abs/2002.11433v2","url_pdf":"https://arxiv.org/pdf/2002.11433v2.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":"efficient-semantic-video-segmentation-with","repo_url":"https://github.com/irfanICMLL/ETC-Real-time-Per-frame-Semantic-video-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-segmentation","task_name":"Video 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/semantic-segmentation-on-camvid","task":"Semantic Segmentation","dataset":"CamVid","model":"ETC-Mobile","rank_in_archive_order":8,"of":21,"metrics":{"Mean IoU":"76.3"},"uses_additional_data":false},{"leaderboard":"/sota/video-semantic-segmentation-on-camvid","task":"Video Semantic Segmentation","dataset":"CamVid","model":"ETC-MobileNet","rank_in_archive_order":2,"of":6,"metrics":{"Mean IoU":"76.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.11433","atlas_url":"https://app.syntology.ai/?focus=2002.11433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.11433"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/irfanICMLL/ETC-Real-time-Per-frame-Semantic-video-segmentation","reach":null}],"summary":{"ran_fixture":1,"unverified":2},"by_repo_kind":{"listed":{"samples":3,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"2046c8aa8a4f99a0","entry":"tensor2img","repo":"irfanICMLL/ETC-Real-time-Per-frame-Semantic-video-segmentation","repo_kind":"listed","path":"tool/eval_tc.py","file_url":"https://github.com/irfanICMLL/ETC-Real-time-Per-frame-Semantic-video-segmentation/blob/HEAD/tool/eval_tc.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2046c8aa8a4f99a0"}},{"code_sha256_prefix":"15f79a6e43b3603e","entry":"normalize","repo":"irfanICMLL/ETC-Real-time-Per-frame-Semantic-video-segmentation","repo_kind":"listed","path":"tool/eval_tc.py","file_url":"https://github.com/irfanICMLL/ETC-Real-time-Per-frame-Semantic-video-segmentation/blob/HEAD/tool/eval_tc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"15f79a6e43b3603e"}},{"code_sha256_prefix":"6f4650f89480bf30","entry":"read_flo","repo":"irfanICMLL/ETC-Real-time-Per-frame-Semantic-video-segmentation","repo_kind":"listed","path":"tool/eval_tc.py","file_url":"https://github.com/irfanICMLL/ETC-Real-time-Per-frame-Semantic-video-segmentation/blob/HEAD/tool/eval_tc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6f4650f89480bf30"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}