{"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/rethinking-the-value-of-labels-for-improving","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","arxiv_id":"2006.07529","date":"2020-06-13","proceeding":"NeurIPS 2020 12","authors":["Yuzhe Yang","Zhi Xu"],"abstract":"Real-world data often exhibits long-tailed distributions with heavy class imbalance, posing great challenges for deep recognition models. We identify a persisting dilemma on the value of labels in the context of imbalanced learning: on the one hand, supervision from labels typically leads to better results than its unsupervised counterparts; on the other hand, heavily imbalanced data naturally incurs \"label bias\" in the classifier, where the decision boundary can be drastically altered by the majority classes. In this work, we systematically investigate these two facets of labels. We demonstrate, theoretically and empirically, that class-imbalanced learning can significantly benefit in both semi-supervised and self-supervised manners. Specifically, we confirm that (1) positively, imbalanced labels are valuable: given more unlabeled data, the original labels can be leveraged with the extra data to reduce label bias in a semi-supervised manner, which greatly improves the final classifier; (2) negatively however, we argue that imbalanced labels are not useful always: classifiers that are first pre-trained in a self-supervised manner consistently outperform their corresponding baselines. Extensive experiments on large-scale imbalanced datasets verify our theoretically grounded strategies, showing superior performance over previous state-of-the-arts. Our intriguing findings highlight the need to rethink the usage of imbalanced labels in realistic long-tailed tasks. Code is available at https://github.com/YyzHarry/imbalanced-semi-self.","url_abs":"https://arxiv.org/abs/2006.07529v2","url_pdf":"https://arxiv.org/pdf/2006.07529v2.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":"rethinking-the-value-of-labels-for-improving","repo_url":"https://github.com/YyzHarry/imbalanced-semi-self","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=10)","model":"LDAM-DRW + SSP","rank_in_archive_order":35,"of":50,"metrics":{"Error Rate":"11.47"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=100)","model":"LDAM-DRW + SSP","rank_in_archive_order":26,"of":28,"metrics":{"Error Rate":"22.17"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=10)","model":"LDAM-DRW + SSP","rank_in_archive_order":27,"of":31,"metrics":{"Error Rate":"41.09"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=100)","model":"LDAM-DRW + SSP","rank_in_archive_order":57,"of":66,"metrics":{"Error Rate":"56.57"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-50","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=50)","model":"LDAM-DRW + SSP","rank_in_archive_order":25,"of":25,"metrics":{"Error Rate":"52.89"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"cRT + SSP","rank_in_archive_order":53,"of":69,"metrics":{"Top-1 Accuracy":"51.3"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"cRT + SSP","rank_in_archive_order":39,"of":43,"metrics":{"Top-1 Accuracy":"68.1%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.07529","atlas_url":"https://app.syntology.ai/?focus=2006.07529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07529"}},"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":"deterministic:regex_extraction","url":"https://github.com/YyzHarry/imbalanced-semi-self","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"e0ad7b46db9af2d8","entry":"validate","repo":"YyzHarry/imbalanced-semi-self","repo_kind":"official","path":"train_semi.py","file_url":"https://github.com/YyzHarry/imbalanced-semi-self/blob/HEAD/train_semi.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":"e0ad7b46db9af2d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}