{"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/continual-semantic-segmentation-via-repulsion","title":"Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations","arxiv_id":"2103.06342","date":"2021-03-10","proceeding":"CVPR 2021 1","authors":["Umberto Michieli","Pietro Zanuttigh"],"abstract":"Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made available over time while previous training data is not retained. The proposed continual learning scheme shapes the latent space to reduce forgetting whilst improving the recognition of novel classes. Our framework is driven by three novel components which we also combine on top of existing techniques effortlessly. First, prototypes matching enforces latent space consistency on old classes, constraining the encoder to produce similar latent representation for previously seen classes in the subsequent steps. Second, features sparsification allows to make room in the latent space to accommodate novel classes. Finally, contrastive learning is employed to cluster features according to their semantics while tearing apart those of different classes. Extensive evaluation on the Pascal VOC2012 and ADE20K datasets demonstrates the effectiveness of our approach, significantly outperforming state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2103.06342v3","url_pdf":"https://arxiv.org/pdf/2103.06342v3.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":[],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"continual-semantic-segmentation","task_name":"Continual Semantic Segmentation"},{"task_slug":"contrastive-learning","task_name":"Contrastive 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":"overlapped-10-1","task_name":"Overlapped 10-1"},{"task_slug":"overlapped-15-1","task_name":"Overlapped 15-1"},{"task_slug":"overlapped-15-5","task_name":"Overlapped 15-5"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/disjoint-10-1-on-pascal-voc-2012","task":"Disjoint 10-1","dataset":"PASCAL VOC 2012","model":"SDR","rank_in_archive_order":4,"of":8,"metrics":{"mIoU":"14.3"},"uses_additional_data":false},{"leaderboard":"/sota/disjoint-15-1-on-pascal-voc-2012","task":"Disjoint 15-1","dataset":"PASCAL VOC 2012","model":"SDR","rank_in_archive_order":5,"of":9,"metrics":{"mIoU":"48.7"},"uses_additional_data":false},{"leaderboard":"/sota/disjoint-15-5-on-pascal-voc-2012","task":"Disjoint 15-5","dataset":"PASCAL VOC 2012","model":"SDR","rank_in_archive_order":5,"of":9,"metrics":{"Mean IoU":"67.3"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-10-1-on-pascal-voc-2012","task":"Overlapped 10-1","dataset":"PASCAL VOC 2012","model":"SDR","rank_in_archive_order":10,"of":13,"metrics":{"mIoU":"25.1"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-15-1-on-pascal-voc-2012","task":"Overlapped 15-1","dataset":"PASCAL VOC 2012","model":"SDR","rank_in_archive_order":10,"of":13,"metrics":{"mIoU":"39.5"},"uses_additional_data":false},{"leaderboard":"/sota/overlapped-15-5-on-pascal-voc-2012","task":"Overlapped 15-5","dataset":"PASCAL VOC 2012","model":"SDR","rank_in_archive_order":8,"of":13,"metrics":{"Mean IoU (val)":"70.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.06342","atlas_url":"https://app.syntology.ai/?focus=2103.06342","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":"2103.06342"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.06342\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.06342"},"call":"get_concepts_for_paper(arxiv_id=\"2103.06342\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1fe6dc01c78952f56ec4d8e2f944943c8dfdbd21a62ba067505d5337c9183598","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}