{"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/psscl-a-progressive-sample-selection","title":"PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels","arxiv_id":null,"date":"2024-12-18","proceeding":"Pattern Recognition 2024 12","authors":["Qian Zhang","Yi Zhu","Filipe R. Cordeiro","Qiu Chen"],"abstract":"Large-scale image datasets frequently contain unavoidable noisy labels, resulting in overfitting in deep neural networks and declining performance. Most existing methods for learning from noisy labels operate as one-stage frameworks, where training data division and semi-supervised learning (SSL) are intertwined for optimization. Accordingly, their effectiveness is significantly influenced by the precision of the separated clean set, prior knowledge of noise, and the robustness of SSL. In this paper, we propose a progressive sample selection framework with contrastive loss for noisy labels named PSSCL. This framework operates in two stages, using robust and contrastive losses to augment the robustness of the model. Stage I focuses on identifying a small clean set through a long-term confidence detection strategy, while stage II aims to enhance performance by expanding this clean set. PSSCL demonstrates significant improvement across various benchmarks when compared with state-of-the-art methods. The code is available at https://github.com/LanXiaoPang613/PSSCL.","url_abs":"https://www.sciencedirect.com/science/article/abs/pii/S0031320324010355","url_pdf":"https://www.sciencedirect.com/science/article/abs/pii/S0031320324010355","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":"psscl-a-progressive-sample-selection","repo_url":"https://github.com/LanXiaoPang613/PSSCL","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"PSSCL (130 epochs)","rank_in_archive_order":13,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"79.68","ImageNet Top-5 Accuracy":"95.16","Top-1 Accuracy":"79.56","Top-5 Accuracy":"94.84"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"PSSCL (120 epochs)","rank_in_archive_order":23,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"79.40","ImageNet Top-5 Accuracy":"94.84","Top-1 Accuracy":"78.52","Top-5 Accuracy":"93.80"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-animal","task":"Learning with noisy labels","dataset":"ANIMAL","model":"PSSCL","rank_in_archive_order":4,"of":19,"metrics":{"Accuracy":"88.74","ImageNet Pretrained":"NO","Network":"Vgg19-BN"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-100n","task":"Learning with noisy labels","dataset":"CIFAR-100N","model":"PSSCL","rank_in_archive_order":3,"of":24,"metrics":{"Accuracy (mean)":"72.00"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n","task":"Learning with noisy labels","dataset":"CIFAR-10N-Aggregate","model":"PSSCL","rank_in_archive_order":2,"of":26,"metrics":{"Accuracy (mean)":"96.41"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-1","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random1","model":"PSSCL","rank_in_archive_order":2,"of":24,"metrics":{"Accuracy (mean)":"96.17"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-2","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random2","model":"PSSCL","rank_in_archive_order":1,"of":23,"metrics":{"Accuracy (mean)":"96.21"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-3","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random3","model":"PSSCL","rank_in_archive_order":1,"of":23,"metrics":{"Accuracy (mean)":"96.49"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-worst","task":"Learning with noisy labels","dataset":"CIFAR-10N-Worst","model":"PSSCL","rank_in_archive_order":2,"of":25,"metrics":{"Accuracy (mean)":"95.12"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-food-101","task":"Learning with noisy labels","dataset":"Food-101","model":"PSSCL","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy (% )":"86.41"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}