{"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/mitigating-background-shift-in-class","title":"Mitigating Background Shift in Class-Incremental Semantic Segmentation","arxiv_id":"2407.11859","date":"2024-07-16","proceeding":null,"authors":["Gilhan Park","WonJun Moon","SuBeen Lee","Tae-Young Kim","Jae-Pil Heo"],"abstract":"Class-Incremental Semantic Segmentation(CISS) aims to learn new classes without forgetting the old ones, using only the labels of the new classes. To achieve this, two popular strategies are employed: 1) pseudo-labeling and knowledge distillation to preserve prior knowledge; and 2) background weight transfer, which leverages the broad coverage of background in learning new classes by transferring background weight to the new class classifier. However, the first strategy heavily relies on the old model in detecting old classes while undetected pixels are regarded as the background, thereby leading to the background shift towards the old classes(i.e., misclassification of old class as background). Additionally, in the case of the second approach, initializing the new class classifier with background knowledge triggers a similar background shift issue, but towards the new classes. To address these issues, we propose a background-class separation framework for CISS. To begin with, selective pseudo-labeling and adaptive feature distillation are to distill only trustworthy past knowledge. On the other hand, we encourage the separation between the background and new classes with a novel orthogonal objective along with label-guided output distillation. Our state-of-the-art results validate the effectiveness of these proposed methods.","url_abs":"https://arxiv.org/abs/2407.11859v1","url_pdf":"https://arxiv.org/pdf/2407.11859v1.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":"mitigating-background-shift-in-class","repo_url":"https://github.com/roadonep/eccv2024_mbs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"class-incremental-semantic-segmentation","task_name":"Class-Incremental Semantic Segmentation"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"continual-semantic-segmentation","task_name":"Continual Semantic Segmentation"},{"task_slug":"disjoint-15-1","task_name":"Disjoint 15-1"},{"task_slug":"disjoint-15-5","task_name":"Disjoint 15-5"},{"task_slug":"disjoint-19-1","task_name":"Disjoint 19-1"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"overlapped-10-1","task_name":"Overlapped 10-1"},{"task_slug":"overlapped-100-10","task_name":"Overlapped 100-10"},{"task_slug":"overlapped-100-5","task_name":"Overlapped 100-5"},{"task_slug":"overlapped-100-50","task_name":"Overlapped 100-50"},{"task_slug":"overlapped-15-1","task_name":"Overlapped 15-1"},{"task_slug":"overlapped-15-5","task_name":"Overlapped 15-5"},{"task_slug":null,"task_name":"Overlapped 19-1"},{"task_slug":"overlapped-5-3","task_name":"Overlapped 5-3"},{"task_slug":"overlapped-50-50","task_name":"Overlapped 50-50"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/disjoint-15-1-on-pascal-voc-2012","task":"Disjoint 15-1","dataset":"PASCAL VOC 2012","model":"MBS","rank_in_archive_order":1,"of":9,"metrics":{"mIoU":"78.1"},"uses_additional_data":false},{"leaderboard":"/sota/disjoint-15-5-on-pascal-voc-2012","task":"Disjoint 15-5","dataset":"PASCAL VOC 2012","model":"MBS","rank_in_archive_order":1,"of":9,"metrics":{"Mean IoU":"79.0"},"uses_additional_data":false},{"leaderboard":"/sota/disjoint-19-1-on-pascal-voc-2012","task":"Disjoint 19-1","dataset":"PASCAL VOC 2012","model":"MBS","rank_in_archive_order":1,"of":1,"metrics":{"mIoU":"82.8"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-10-1-on-pascal-voc-2012","task":"Overlapped 10-1","dataset":"PASCAL VOC 2012","model":"MBS","rank_in_archive_order":1,"of":13,"metrics":{"mIoU":"77.19"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-100-10-on-ade20k","task":"Overlapped 100-10","dataset":"ADE20K","model":"MBS","rank_in_archive_order":1,"of":6,"metrics":{"Mean IoU (test) ":"44.5"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-100-5-on-ade20k","task":"Overlapped 100-5","dataset":"ADE20K","model":"MBS","rank_in_archive_order":1,"of":8,"metrics":{"mIoU":"42.8"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-100-50-on-ade20k","task":"Overlapped 100-50","dataset":"ADE20K","model":"MBS","rank_in_archive_order":1,"of":7,"metrics":{"mIoU":"45.7"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-15-1-on-pascal-voc-2012","task":"Overlapped 15-1","dataset":"PASCAL VOC 2012","model":"MBS","rank_in_archive_order":1,"of":13,"metrics":{"mIoU":"80.6"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-15-5-on-pascal-voc-2012","task":"Overlapped 15-5","dataset":"PASCAL VOC 2012","model":"MBS","rank_in_archive_order":1,"of":13,"metrics":{"Mean IoU (val)":"82.6"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-5-3-on-pascal-voc-2012","task":"Overlapped 5-3","dataset":"PASCAL VOC 2012","model":"MBS","rank_in_archive_order":1,"of":4,"metrics":{"Mean IoU (test)":"78.1"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-50-50-on-ade20k","task":"Overlapped 50-50","dataset":"ADE20K","model":"MBS","rank_in_archive_order":1,"of":7,"metrics":{"mIoU":"45.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.11859","atlas_url":"https://app.syntology.ai/?focus=2407.11859","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":"2407.11859"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2407.11859\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2407.11859"},"call":"get_concepts_for_paper(arxiv_id=\"2407.11859\")"}],"by_repo":[{"repo":"roadonep/eccv2024_mbs","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"dc6bc45800c0276fb6289b0ffbed2292ce28deead6d5d55bf0e89166f895fc2d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}