{"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/revisiting-adversarial-training-for-the-worst","title":"Revisiting adversarial training for the worst-performing class","arxiv_id":"2302.08872","date":"2023-02-17","proceeding":null,"authors":["Thomas Pethick","Grigorios G. Chrysos","Volkan Cevher"],"abstract":"Despite progress in adversarial training (AT), there is a substantial gap between the top-performing and worst-performing classes in many datasets. For example, on CIFAR10, the accuracies for the best and worst classes are 74% and 23%, respectively. We argue that this gap can be reduced by explicitly optimizing for the worst-performing class, resulting in a min-max-max optimization formulation. Our method, called class focused online learning (CFOL), includes high probability convergence guarantees for the worst class loss and can be easily integrated into existing training setups with minimal computational overhead. We demonstrate an improvement to 32% in the worst class accuracy on CIFAR10, and we observe consistent behavior across CIFAR100 and STL10. Our study highlights the importance of moving beyond average accuracy, which is particularly important in safety-critical applications.","url_abs":"https://arxiv.org/abs/2302.08872v1","url_pdf":"https://arxiv.org/pdf/2302.08872v1.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":"revisiting-adversarial-training-for-the-worst","repo_url":"https://github.com/lions-epfl/class-focused-online-learning-code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.08872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08872"}},"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/lions-epfl/class-focused-online-learning-code","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"1153837ba4a94242","entry":"PreActResNet18","repo":"lions-epfl/class-focused-online-learning-code","repo_kind":"official","path":"cfol/preactresnet.py","file_url":"https://github.com/lions-epfl/class-focused-online-learning-code/blob/HEAD/cfol/preactresnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1153837ba4a94242"}},{"code_sha256_prefix":"45fa5e2bab02ccef","entry":"CB_loss","repo":"lions-epfl/class-focused-online-learning-code","repo_kind":"official","path":"cfol/focal_loss.py","file_url":"https://github.com/lions-epfl/class-focused-online-learning-code/blob/HEAD/cfol/focal_loss.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":"45fa5e2bab02ccef"}},{"code_sha256_prefix":"388b2e0ffc9f3246","entry":"check_data_exists","repo":"lions-epfl/class-focused-online-learning-code","repo_kind":"official","path":"cfol/imagenette_dataset.py","file_url":"https://github.com/lions-epfl/class-focused-online-learning-code/blob/HEAD/cfol/imagenette_dataset.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":"388b2e0ffc9f3246"}},{"code_sha256_prefix":"4bebda9ddfdffe0a","entry":"focal_loss","repo":"lions-epfl/class-focused-online-learning-code","repo_kind":"official","path":"cfol/focal_loss.py","file_url":"https://github.com/lions-epfl/class-focused-online-learning-code/blob/HEAD/cfol/focal_loss.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":"4bebda9ddfdffe0a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}