{"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/early-preparation-pays-off-new-classifier-pre","title":"Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation","arxiv_id":"2407.14142","date":"2024-07-19","proceeding":null,"authors":["Zhengyuan Xie","Haiquan Lu","Jia-Wen Xiao","Enguang Wang","Le Zhang","Xialei Liu"],"abstract":"Class incremental semantic segmentation aims to preserve old knowledge while learning new tasks, however, it is impeded by catastrophic forgetting and background shift issues. Prior works indicate the pivotal importance of initializing new classifiers and mainly focus on transferring knowledge from the background classifier or preparing classifiers for future classes, neglecting the flexibility and variance of new classifiers. In this paper, we propose a new classifier pre-tuning~(NeST) method applied before the formal training process, learning a transformation from old classifiers to generate new classifiers for initialization rather than directly tuning the parameters of new classifiers. Our method can make new classifiers align with the backbone and adapt to the new data, preventing drastic changes in the feature extractor when learning new classes. Besides, we design a strategy considering the cross-task class similarity to initialize matrices used in the transformation, helping achieve the stability-plasticity trade-off. Experiments on Pascal VOC 2012 and ADE20K datasets show that the proposed strategy can significantly improve the performance of previous methods. The code is available at \\url{https://github.com/zhengyuan-xie/ECCV24_NeST}.","url_abs":"https://arxiv.org/abs/2407.14142v1","url_pdf":"https://arxiv.org/pdf/2407.14142v1.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":"early-preparation-pays-off-new-classifier-pre","repo_url":"https://github.com/zhengyuan-xie/eccv24_nest","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"class-incremental-semantic-segmentation","task_name":"Class-Incremental Semantic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.14142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14142"}},"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":"deterministic:regex_extraction","url":"https://github.com/zhengyuan-xie/ECCV24_NeST","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran":3,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"144d10b49baeb8a6","entry":"window_partition","repo":"zhengyuan-xie/ECCV24_NeST","repo_kind":"official","path":"models/swin.py","file_url":"https://github.com/zhengyuan-xie/ECCV24_NeST/blob/HEAD/models/swin.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"f5ab76486eeab7b9","entry":"drop_path","repo":"zhengyuan-xie/ECCV24_NeST","repo_kind":"official","path":"modules/backbone.py","file_url":"https://github.com/zhengyuan-xie/ECCV24_NeST/blob/HEAD/modules/backbone.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f5ab76486eeab7b9"}},{"code_sha256_prefix":"7f8043e7dd6c2735","entry":"flip","repo":"zhengyuan-xie/ECCV24_NeST","repo_kind":"official","path":"segmentation_module.py","file_url":"https://github.com/zhengyuan-xie/ECCV24_NeST/blob/HEAD/segmentation_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7f8043e7dd6c2735"}},{"code_sha256_prefix":"1de18d992c154e8d","entry":"modify_command_options","repo":"zhengyuan-xie/ECCV24_NeST","repo_kind":"official","path":"argparser.py","file_url":"https://github.com/zhengyuan-xie/ECCV24_NeST/blob/HEAD/argparser.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1de18d992c154e8d"}},{"code_sha256_prefix":"b64b3a89bb583437","entry":"trunc_normal_","repo":"zhengyuan-xie/ECCV24_NeST","repo_kind":"official","path":"modules/backbone.py","file_url":"https://github.com/zhengyuan-xie/ECCV24_NeST/blob/HEAD/modules/backbone.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b64b3a89bb583437"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"zhengyuan-xie/ECCV24_NeST","repo_kind":"official","path":"models/swin.py","file_url":"https://github.com/zhengyuan-xie/ECCV24_NeST/blob/HEAD/models/swin.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}