{"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/rehearsal-revealed-the-limits-and-merits-of","title":"Rehearsal revealed: The limits and merits of revisiting samples in continual learning","arxiv_id":"2104.07446","date":"2021-04-15","proceeding":"ICCV 2021 10","authors":["Eli Verwimp","Matthias De Lange","Tinne Tuytelaars"],"abstract":"Learning from non-stationary data streams and overcoming catastrophic forgetting still poses a serious challenge for machine learning research. Rather than aiming to improve state-of-the-art, in this work we provide insight into the limits and merits of rehearsal, one of continual learning's most established methods. We hypothesize that models trained sequentially with rehearsal tend to stay in the same low-loss region after a task has finished, but are at risk of overfitting on its sample memory, hence harming generalization. We provide both conceptual and strong empirical evidence on three benchmarks for both behaviors, bringing novel insights into the dynamics of rehearsal and continual learning in general. Finally, we interpret important continual learning works in the light of our findings, allowing for a deeper understanding of their successes.","url_abs":"https://arxiv.org/abs/2104.07446v1","url_pdf":"https://arxiv.org/pdf/2104.07446v1.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":"rehearsal-revealed-the-limits-and-merits-of","repo_url":"https://github.com/Mattdl/RehearsalRevealed","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.07446","atlas_url":"https://app.syntology.ai/?focus=2104.07446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07446"}},"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/Mattdl/RehearsalRevealed","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"583f9780bdd00a45","entry":"conv3x3","repo":"Mattdl/RehearsalRevealed","repo_kind":"official","path":"ridge_aversion_exp/model.py","file_url":"https://github.com/Mattdl/RehearsalRevealed/blob/HEAD/ridge_aversion_exp/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"583f9780bdd00a45"}},{"code_sha256_prefix":"f321f54723433661","entry":"pil_loader","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f321f54723433661"}},{"code_sha256_prefix":"b03f148b0213ab66","entry":"ResNet18","repo":"Mattdl/RehearsalRevealed","repo_kind":"official","path":"ridge_aversion_exp/model.py","file_url":"https://github.com/Mattdl/RehearsalRevealed/blob/HEAD/ridge_aversion_exp/model.py","link_basis":"first_harvest_node","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":"b03f148b0213ab66"}},{"code_sha256_prefix":"5f3b1c7207af014b","entry":"calc_full_grad_norm","repo":"Mattdl/RehearsalRevealed","repo_kind":"official","path":"grad_norm_exp/grad_norms.py","file_url":"https://github.com/Mattdl/RehearsalRevealed/blob/HEAD/grad_norm_exp/grad_norms.py","link_basis":"first_harvest_node","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":"5f3b1c7207af014b"}},{"code_sha256_prefix":"4ac54a7e815a9d58","entry":"get_single_label_mnist","repo":"Mattdl/RehearsalRevealed","repo_kind":"official","path":"framework/cole/core.py","file_url":"https://github.com/Mattdl/RehearsalRevealed/blob/HEAD/framework/cole/core.py","link_basis":"first_harvest_node","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":"4ac54a7e815a9d58"}},{"code_sha256_prefix":"55bf3bcd2870630b","entry":"get_split_cifar10","repo":"Mattdl/RehearsalRevealed","repo_kind":"official","path":"framework/cole/core.py","file_url":"https://github.com/Mattdl/RehearsalRevealed/blob/HEAD/framework/cole/core.py","link_basis":"first_harvest_node","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":"55bf3bcd2870630b"}},{"code_sha256_prefix":"31b613cae5ceb8b8","entry":"get_split_mini_imagenet","repo":"Mattdl/RehearsalRevealed","repo_kind":"official","path":"ridge_aversion_exp/miniimagenet.py","file_url":"https://github.com/Mattdl/RehearsalRevealed/blob/HEAD/ridge_aversion_exp/miniimagenet.py","link_basis":"first_harvest_node","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":"31b613cae5ceb8b8"}},{"code_sha256_prefix":"8e18f937db588ef5","entry":"get_split_mnist","repo":"Mattdl/RehearsalRevealed","repo_kind":"official","path":"framework/cole/core.py","file_url":"https://github.com/Mattdl/RehearsalRevealed/blob/HEAD/framework/cole/core.py","link_basis":"first_harvest_node","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":"8e18f937db588ef5"}},{"code_sha256_prefix":"d8513af311af3e75","entry":"merge_paths","repo":"Mattdl/RehearsalRevealed","repo_kind":"official","path":"grad_norm_exp/grad_norms_plot.py","file_url":"https://github.com/Mattdl/RehearsalRevealed/blob/HEAD/grad_norm_exp/grad_norms_plot.py","link_basis":"first_harvest_node","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":"d8513af311af3e75"}},{"code_sha256_prefix":"3df54e3aaa048117","entry":"rescale_model_coords","repo":"Mattdl/RehearsalRevealed","repo_kind":"official","path":"contour_exp/mode_connectivity_plot.py","file_url":"https://github.com/Mattdl/RehearsalRevealed/blob/HEAD/contour_exp/mode_connectivity_plot.py","link_basis":"first_harvest_node","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":"3df54e3aaa048117"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}