{"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/a-generative-appearance-model-for-end-to-end","title":"A Generative Appearance Model for End-to-end Video Object Segmentation","arxiv_id":"1811.11611","date":"2018-11-28","proceeding":"CVPR 2019 6","authors":["Joakim Johnander","Martin Danelljan","Emil Brissman","Fahad Shahbaz Khan","Michael Felsberg"],"abstract":"One of the fundamental challenges in video object segmentation is to find an\neffective representation of the target and background appearance. The best\nperforming approaches resort to extensive fine-tuning of a convolutional neural\nnetwork for this purpose. Besides being prohibitively expensive, this strategy\ncannot be truly trained end-to-end since the online fine-tuning procedure is\nnot integrated into the offline training of the network.\n  To address these issues, we propose a network architecture that learns a\npowerful representation of the target and background appearance in a single\nforward pass. The introduced appearance module learns a probabilistic\ngenerative model of target and background feature distributions. Given a new\nimage, it predicts the posterior class probabilities, providing a highly\ndiscriminative cue, which is processed in later network modules. Both the\nlearning and prediction stages of our appearance module are fully\ndifferentiable, enabling true end-to-end training of the entire segmentation\npipeline. Comprehensive experiments demonstrate the effectiveness of the\nproposed approach on three video object segmentation benchmarks. We close the\ngap to approaches based on online fine-tuning on DAVIS17, while operating at 15\nFPS on a single GPU. Furthermore, our method outperforms all published\napproaches on the large-scale YouTube-VOS dataset.","url_abs":"http://arxiv.org/abs/1811.11611v2","url_pdf":"http://arxiv.org/pdf/1811.11611v2.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":"a-generative-appearance-model-for-end-to-end","repo_url":"https://github.com/joakimjohnander/agame-vos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"one-shot-visual-object-segmentation","task_name":"One-shot visual object segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"AGAME","rank_in_archive_order":56,"of":78,"metrics":{"F-measure (Decay)":"9.8","F-measure (Mean)":"82.2","F-measure (Recall)":"90.3","J&F":"81.85","Jaccard (Decay)":"9.4","Jaccard (Mean)":"81.5","Jaccard (Recall)":"93.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"AGAME","rank_in_archive_order":53,"of":59,"metrics":{"F-measure (Decay)":"27.6","F-measure (Mean)":"55.3","F-measure (Recall)":"61.1","J&F":"52.3","Jaccard (Decay)":"28.9","Jaccard (Mean)":"49.2","Jaccard (Recall)":"53.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"AGAME","rank_in_archive_order":58,"of":81,"metrics":{"F-measure (Decay)":"15.8","F-measure (Mean)":"73.6","F-measure (Recall)":"83.4","J&F":"71.05","Jaccard (Decay)":"14.0","Jaccard (Mean)":"68.5","Jaccard (Recall)":"78.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.11611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11611"}},"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/joakimjohnander/agame-vos","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"7a922bc51e6def59","entry":"get_required_padding","repo":"joakimjohnander/agame-vos","repo_kind":"listed","path":"models/agame_model.py","file_url":"https://github.com/joakimjohnander/agame-vos/blob/HEAD/models/agame_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7a922bc51e6def59"}},{"code_sha256_prefix":"b1e078b98b75fbcd","entry":"softmax_aggregate","repo":"joakimjohnander/agame-vos","repo_kind":"listed","path":"models/agame_model.py","file_url":"https://github.com/joakimjohnander/agame-vos/blob/HEAD/models/agame_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1e078b98b75fbcd"}},{"code_sha256_prefix":"bb0b5f51d1508b00","entry":"apply_padding","repo":"joakimjohnander/agame-vos","repo_kind":"listed","path":"models/agame_model.py","file_url":"https://github.com/joakimjohnander/agame-vos/blob/HEAD/models/agame_model.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":"bb0b5f51d1508b00"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}