{"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/incremental-learning-techniques-for-semantic","title":"Incremental Learning Techniques for Semantic Segmentation","arxiv_id":"1907.13372","date":"2019-07-31","proceeding":null,"authors":["Umberto Michieli","Pietro Zanuttigh"],"abstract":"Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object detection while in this work we formally introduce the incremental learning problem for semantic segmentation in which a pixel-wise labeling is considered. To tackle this task we propose to distill the knowledge of the previous model to retain the information about previously learned classes, whilst updating the current model to learn the new ones. We propose various approaches working both on the output logits and on intermediate features. In opposition to some recent frameworks, we do not store any image from previously learned classes and only the last model is needed to preserve high accuracy on these classes. The experimental evaluation on the Pascal VOC2012 dataset shows the effectiveness of the proposed approaches.","url_abs":"https://arxiv.org/abs/1907.13372v4","url_pdf":"https://arxiv.org/pdf/1907.13372v4.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":"incremental-learning-techniques-for-semantic","repo_url":"https://github.com/LTTM/IL-SemSegm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"incremental-learning-techniques-for-semantic","repo_url":"https://github.com/MECLabTUDA/ACS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":"image-classification","task_name":"Image Classification"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"overlapped-10-1","task_name":"Overlapped 10-1"},{"task_slug":"overlapped-100-5","task_name":"Overlapped 100-5"},{"task_slug":"overlapped-15-1","task_name":"Overlapped 15-1"},{"task_slug":"overlapped-15-5","task_name":"Overlapped 15-5"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/disjoint-10-1-on-pascal-voc-2012","task":"Disjoint 10-1","dataset":"PASCAL VOC 2012","model":"ILT","rank_in_archive_order":7,"of":8,"metrics":{"mIoU":"5.4"},"uses_additional_data":false},{"leaderboard":"/sota/disjoint-15-1-on-pascal-voc-2012","task":"Disjoint 15-1","dataset":"PASCAL VOC 2012","model":"ILT","rank_in_archive_order":8,"of":9,"metrics":{"mIoU":"7.9"},"uses_additional_data":false},{"leaderboard":"/sota/disjoint-15-5-on-pascal-voc-2012","task":"Disjoint 15-5","dataset":"PASCAL VOC 2012","model":"ILT","rank_in_archive_order":8,"of":9,"metrics":{"Mean IoU":"58.9"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-10-1-on-pascal-voc-2012","task":"Overlapped 10-1","dataset":"PASCAL VOC 2012","model":"ILT","rank_in_archive_order":12,"of":13,"metrics":{"mIoU":"5.5"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-100-5-on-ade20k","task":"Overlapped 100-5","dataset":"ADE20K","model":"ILT","rank_in_archive_order":8,"of":8,"metrics":{"mIoU":"0.5"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-15-1-on-pascal-voc-2012","task":"Overlapped 15-1","dataset":"PASCAL VOC 2012","model":"ILT","rank_in_archive_order":12,"of":13,"metrics":{"mIoU":"9.2"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-15-5-on-pascal-voc-2012","task":"Overlapped 15-5","dataset":"PASCAL VOC 2012","model":"ILT","rank_in_archive_order":12,"of":13,"metrics":{"Mean IoU (val)":"61.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.13372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.13372"}},"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/LTTM/IL-SemSegm","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MECLabTUDA/ACS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"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":"2219b85d7a88aae2","entry":"parse_args","repo":"MECLabTUDA/ACS","repo_kind":"listed","path":"args.py","file_url":"https://github.com/MECLabTUDA/ACS/blob/HEAD/args.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":"2219b85d7a88aae2"}},{"code_sha256_prefix":"98100837a73e9e94","entry":"parse_args_as_dict","repo":"MECLabTUDA/ACS","repo_kind":"listed","path":"args.py","file_url":"https://github.com/MECLabTUDA/ACS/blob/HEAD/args.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":"98100837a73e9e94"}},{"code_sha256_prefix":"aa27793b570440a2","entry":"parse_dict_as_args","repo":"MECLabTUDA/ACS","repo_kind":"listed","path":"args.py","file_url":"https://github.com/MECLabTUDA/ACS/blob/HEAD/args.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":"aa27793b570440a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}