{"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/understanding-catastrophic-forgetting-and","title":"Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping","arxiv_id":"2102.11343","date":"2021-02-22","proceeding":null,"authors":["Prakhar Kaushik","Alex Gain","Adam Kortylewski","Alan Yuille"],"abstract":"Catastrophic forgetting in neural networks is a significant problem for continual learning. A majority of the current methods replay previous data during training, which violates the constraints of an ideal continual learning system. Additionally, current approaches that deal with forgetting ignore the problem of catastrophic remembering, i.e. the worsening ability to discriminate between data from different tasks. In our work, we introduce Relevance Mapping Networks (RMNs) which are inspired by the Optimal Overlap Hypothesis. The mappings reflects the relevance of the weights for the task at hand by assigning large weights to essential parameters. We show that RMNs learn an optimized representational overlap that overcomes the twin problem of catastrophic forgetting and remembering. Our approach achieves state-of-the-art performance across all common continual learning datasets, even significantly outperforming data replay methods while not violating the constraints for an ideal continual learning system. Moreover, RMNs retain the ability to detect data from new tasks in an unsupervised manner, thus proving their resilience against catastrophic remembering.","url_abs":"https://arxiv.org/abs/2102.11343v1","url_pdf":"https://arxiv.org/pdf/2102.11343v1.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":"understanding-catastrophic-forgetting-and","repo_url":"https://gitlab.com/prakhark2/relevance-mapping-networks","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/continual-learning-on-cifar100-10-tasks","task":"Continual Learning","dataset":"Cifar100 (10 tasks)","model":"RMN (Resnet)","rank_in_archive_order":3,"of":5,"metrics":{"Average Accuracy":"84.9"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-cifar100-20-tasks","task":"Continual Learning","dataset":"Cifar100 (20 tasks)","model":"RMN","rank_in_archive_order":4,"of":9,"metrics":{"Average Accuracy":"81"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-imagenet-50-5-tasks","task":"Continual Learning","dataset":"ImageNet-50 (5 tasks)","model":"RMN","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"68.1"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-permuted-mnist","task":"Continual Learning","dataset":"Permuted MNIST","model":"RMN","rank_in_archive_order":1,"of":3,"metrics":{"Average Accuracy":"97.988","MLP Hidden Layers-width":"2-100","Pretrained/Transfer Learning":"No"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.11343","atlas_url":"https://app.syntology.ai/?focus=2102.11343","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":"2102.11343"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2102.11343\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2102.11343"},"call":"get_concepts_for_paper(arxiv_id=\"2102.11343\")"}],"by_repo":[{"repo":"gitlab.com/prakhark2/relevance-mapping-networks","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"38837b4f8753dd1ee3aed8da3025c0c9fa5668439afedc89ee24ba96c66298d8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}