{"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/two-wrongs-don-t-make-a-right-combating","title":"Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise","arxiv_id":"2112.02960","date":"2021-12-06","proceeding":null,"authors":["Mingcai Chen","Hao Cheng","Yuntao Du","Ming Xu","Wenyu Jiang","Chongjun Wang"],"abstract":"Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could result in a loss of information, especially when the corruption has a dependency on data, e.g., class-dependent or instance-dependent. Moreover, from the training dynamics of a representative two-stage method DivideMix, we identify the domination of confirmation bias: pseudo-labels fail to correct a considerable amount of noisy labels, and consequently, the errors accumulate. To sufficiently exploit information from noisy labels and mitigate wrong corrections, we propose Robust Label Refurbishment (Robust LR) a new hybrid method that integrates pseudo-labeling and confidence estimation techniques to refurbish noisy labels. We show that our method successfully alleviates the damage of both label noise and confirmation bias. As a result, it achieves state-of-the-art performance across datasets and noise types, namely CIFAR under different levels of synthetic noise and Mini-WebVision and ANIMAL-10N with real-world noise.","url_abs":"https://arxiv.org/abs/2112.02960v3","url_pdf":"https://arxiv.org/pdf/2112.02960v3.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":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"Robust LR","rank_in_archive_order":2,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"75.48","ImageNet Top-5 Accuracy":"93.76","Top-1 Accuracy":"81.84","Top-5 Accuracy":"94.12"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.02960","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}