{"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/modeling-the-background-for-incremental","title":"Modeling the Background for Incremental Learning in Semantic Segmentation","arxiv_id":"2002.00718","date":"2020-02-03","proceeding":"CVPR 2020 6","authors":["Fabio Cermelli","Massimiliano Mancini","Samuel Rota Bulò","Elisa Ricci","Barbara Caputo"],"abstract":"Despite their effectiveness in a wide range of tasks, deep architectures suffer from some important limitations. In particular, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are required to update their model as new classes are available but the original training set is not retained. This paper addresses this problem in the context of semantic segmentation. Current strategies fail on this task because they do not consider a peculiar aspect of semantic segmentation: since each training step provides annotation only for a subset of all possible classes, pixels of the background class (i.e. pixels that do not belong to any other classes) exhibit a semantic distribution shift. In this work we revisit classical incremental learning methods, proposing a new distillation-based framework which explicitly accounts for this shift. Furthermore, we introduce a novel strategy to initialize classifier's parameters, thus preventing biased predictions toward the background class. We demonstrate the effectiveness of our approach with an extensive evaluation on the Pascal-VOC 2012 and ADE20K datasets, significantly outperforming state of the art incremental learning methods.","url_abs":"https://arxiv.org/abs/2002.00718v2","url_pdf":"https://arxiv.org/pdf/2002.00718v2.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":"modeling-the-background-for-incremental","repo_url":"https://github.com/fcdl94/MiB","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"disjoint-10-1","task_name":"Disjoint 10-1"},{"task_slug":"disjoint-15-1","task_name":"Disjoint 15-1"},{"task_slug":"disjoint-15-5","task_name":"Disjoint 15-5"},{"task_slug":"domain-1-1","task_name":"Domain 1-1"},{"task_slug":"domain-11-1","task_name":"Domain 11-1"},{"task_slug":"domain-11-5","task_name":"Domain 11-5"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"overlapped-10-1","task_name":"Overlapped 10-1"},{"task_slug":null,"task_name":"Overlapped 19-1"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/disjoint-10-1-on-pascal-voc-2012","task":"Disjoint 10-1","dataset":"PASCAL VOC 2012","model":"MiB","rank_in_archive_order":6,"of":8,"metrics":{"mIoU":"6.9"},"uses_additional_data":false},{"leaderboard":"/sota/disjoint-15-1-on-pascal-voc-2012","task":"Disjoint 15-1","dataset":"PASCAL VOC 2012","model":"MiB","rank_in_archive_order":7,"of":9,"metrics":{"mIoU":"39.9"},"uses_additional_data":false},{"leaderboard":"/sota/disjoint-15-5-on-pascal-voc-2012","task":"Disjoint 15-5","dataset":"PASCAL VOC 2012","model":"MiB","rank_in_archive_order":6,"of":9,"metrics":{"Mean IoU":"65.9"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-10-1-on-pascal-voc-2012","task":"Overlapped 10-1","dataset":"PASCAL VOC 2012","model":"MiB","rank_in_archive_order":11,"of":13,"metrics":{"mIoU":"20.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.00718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.00718"}},"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/fcdl94/MiB","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"named_in_paper":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"7f8043e7dd6c2735","entry":"flip","repo":"fcdl94/MiB","repo_kind":"named_in_paper","path":"segmentation_module.py","file_url":"https://github.com/fcdl94/MiB/blob/HEAD/segmentation_module.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":"7f8043e7dd6c2735"}},{"code_sha256_prefix":"21c634fc9f57dd4c","entry":"filter_images","repo":"fcdl94/MiB","repo_kind":"named_in_paper","path":"dataset/utils.py","file_url":"https://github.com/fcdl94/MiB/blob/HEAD/dataset/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":"21c634fc9f57dd4c"}},{"code_sha256_prefix":"1d5ab3d2728d692e","entry":"get_loss","repo":"fcdl94/MiB","repo_kind":"named_in_paper","path":"utils/loss.py","file_url":"https://github.com/fcdl94/MiB/blob/HEAD/utils/loss.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":"1d5ab3d2728d692e"}},{"code_sha256_prefix":"1803646c9607e58b","entry":"get_per_task_classes","repo":"fcdl94/MiB","repo_kind":"named_in_paper","path":"tasks.py","file_url":"https://github.com/fcdl94/MiB/blob/HEAD/tasks.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":"1803646c9607e58b"}},{"code_sha256_prefix":"ad850a613acafcc0","entry":"get_task_labels","repo":"fcdl94/MiB","repo_kind":"named_in_paper","path":"tasks.py","file_url":"https://github.com/fcdl94/MiB/blob/HEAD/tasks.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":"ad850a613acafcc0"}},{"code_sha256_prefix":"afc11e8a9f0184d3","entry":"group_images","repo":"fcdl94/MiB","repo_kind":"named_in_paper","path":"dataset/utils.py","file_url":"https://github.com/fcdl94/MiB/blob/HEAD/dataset/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":"afc11e8a9f0184d3"}},{"code_sha256_prefix":"dcde5d7316c65773","entry":"modify_command_options","repo":"fcdl94/MiB","repo_kind":"named_in_paper","path":"argparser.py","file_url":"https://github.com/fcdl94/MiB/blob/HEAD/argparser.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":"dcde5d7316c65773"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}