{"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/attribution-aware-weight-transfer-a-warm","title":"Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation","arxiv_id":"2210.07207","date":"2022-10-13","proceeding":null,"authors":["Dipam Goswami","René Schuster","Joost Van de Weijer","Didier Stricker"],"abstract":"In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift. Although recent works focused on these issues, existing classifier initialization methods do not address the background shift problem and assign the same initialization weights to both background and new foreground class classifiers. We propose to address the background shift with a novel classifier initialization method which employs gradient-based attribution to identify the most relevant weights for new classes from the classifier's weights for the previous background and transfers these weights to the new classifier. This warm-start weight initialization provides a general solution applicable to several CISS methods. Furthermore, it accelerates learning of new classes while mitigating forgetting. Our experiments demonstrate significant improvement in mIoU compared to the state-of-the-art CISS methods on the Pascal-VOC 2012, ADE20K and Cityscapes datasets.","url_abs":"https://arxiv.org/abs/2210.07207v1","url_pdf":"https://arxiv.org/pdf/2210.07207v1.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":"attribution-aware-weight-transfer-a-warm","repo_url":"https://github.com/dfki-av/awt-for-ciss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"class-incremental-semantic-segmentation","task_name":"Class-Incremental Semantic Segmentation"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"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-14-1","task_name":"Overlapped 14-1"},{"task_slug":"overlapped-15-1","task_name":"Overlapped 15-1"},{"task_slug":"overlapped-15-5","task_name":"Overlapped 15-5"},{"task_slug":"overlapped-5-3","task_name":"Overlapped 5-3"},{"task_slug":"overlapped-50-50","task_name":"Overlapped 50-50"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/overlapped-10-1-on-cityscapes","task":"Overlapped 10-1","dataset":"Cityscapes","model":"MiB+AWT","rank_in_archive_order":1,"of":1,"metrics":{"mIoU":"44.9"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-10-1-on-pascal-voc-2012","task":"Overlapped 10-1","dataset":"PASCAL VOC 2012","model":"SSUL+AWT","rank_in_archive_order":5,"of":13,"metrics":{"mIoU":"60.7"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-100-10-on-ade20k","task":"Overlapped 100-10","dataset":"ADE20K","model":"MiB+AWT","rank_in_archive_order":3,"of":6,"metrics":{"Mean IoU (test) ":"33.2"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-100-5-on-ade20k","task":"Overlapped 100-5","dataset":"ADE20K","model":"MiB+AWT","rank_in_archive_order":4,"of":8,"metrics":{"mIoU":"31.1"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-100-50-on-ade20k","task":"Overlapped 100-50","dataset":"ADE20K","model":"MiB+AWT","rank_in_archive_order":2,"of":7,"metrics":{"mIoU":"35.6"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-14-1-on-cityscapes","task":"Overlapped 14-1","dataset":"Cityscapes","model":"MiB+AWT","rank_in_archive_order":1,"of":1,"metrics":{"mIoU":"46.9"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-15-1-on-pascal-voc-2012","task":"Overlapped 15-1","dataset":"PASCAL VOC 2012","model":"SSUL+AWT","rank_in_archive_order":6,"of":13,"metrics":{"mIoU":"67.6"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-15-5-on-pascal-voc-2012","task":"Overlapped 15-5","dataset":"PASCAL VOC 2012","model":"SSUL+AWT","rank_in_archive_order":6,"of":13,"metrics":{"Mean IoU (val)":"71.4"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-5-3-on-pascal-voc-2012","task":"Overlapped 5-3","dataset":"PASCAL VOC 2012","model":"SSUL+AWT","rank_in_archive_order":4,"of":4,"metrics":{"Mean IoU (test)":"57.1"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-50-50-on-ade20k","task":"Overlapped 50-50","dataset":"ADE20K","model":"MiB+AWT","rank_in_archive_order":2,"of":7,"metrics":{"mIoU":"33.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.07207","atlas_url":"https://app.syntology.ai/?focus=2210.07207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07207"}},"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/dfki-av/awt-for-ciss","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":"dfki-av/awt-for-ciss","repo_kind":"official","path":"segmentation_module.py","file_url":"https://github.com/dfki-av/awt-for-ciss/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":"178a3050bc16f2e5","entry":"get_per_task_classes","repo":"dfki-av/awt-for-ciss","repo_kind":"official","path":"tasks.py","file_url":"https://github.com/dfki-av/awt-for-ciss/blob/HEAD/tasks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"178a3050bc16f2e5"}},{"code_sha256_prefix":"8aaaf28fe82763c9","entry":"get_task_labels","repo":"dfki-av/awt-for-ciss","repo_kind":"official","path":"tasks.py","file_url":"https://github.com/dfki-av/awt-for-ciss/blob/HEAD/tasks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8aaaf28fe82763c9"}},{"code_sha256_prefix":"0a93283e9a1abf38","entry":"get_task_labels_attr","repo":"dfki-av/awt-for-ciss","repo_kind":"official","path":"tasks.py","file_url":"https://github.com/dfki-av/awt-for-ciss/blob/HEAD/tasks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a93283e9a1abf38"}},{"code_sha256_prefix":"8f85871d3af5c3c3","entry":"modify_command_options","repo":"dfki-av/awt-for-ciss","repo_kind":"official","path":"argparser.py","file_url":"https://github.com/dfki-av/awt-for-ciss/blob/HEAD/argparser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f85871d3af5c3c3"}},{"code_sha256_prefix":"887fce52f90eb3b2","entry":"soft_crossentropy","repo":"dfki-av/awt-for-ciss","repo_kind":"official","path":"utils/loss.py","file_url":"https://github.com/dfki-av/awt-for-ciss/blob/HEAD/utils/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"887fce52f90eb3b2"}},{"code_sha256_prefix":"90ca9d04a07dfe93","entry":"get_loss","repo":"dfki-av/awt-for-ciss","repo_kind":"official","path":"utils/loss.py","file_url":"https://github.com/dfki-av/awt-for-ciss/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":"90ca9d04a07dfe93"}},{"code_sha256_prefix":"b494dd1e415df215","entry":"nca","repo":"dfki-av/awt-for-ciss","repo_kind":"official","path":"utils/loss.py","file_url":"https://github.com/dfki-av/awt-for-ciss/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":"b494dd1e415df215"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}