{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:38:04Z","timestamp":1763192284235,"version":"3.45.0"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227884","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Robust-CLIP: End-to-End Fine-Tuning of Vision-Language Models under Noisy Labels"],"prefix":"10.1109","author":[{"given":"Guanyu","family":"Chen","sequence":"first","affiliation":[{"name":"Intelligent Game and Decision Lab(IGDL),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihao","family":"Li","sequence":"additional","affiliation":[{"name":"Intelligent Game and Decision Lab(IGDL),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Defu","family":"Liu","sequence":"additional","affiliation":[{"name":"Intelligent Game and Decision Lab(IGDL),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Yi","sequence":"additional","affiliation":[{"name":"Intelligent Game and Decision Lab(IGDL),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li","key":"ref1"},{"key":"ref2","article-title":"Coca: Contrastive captioners are image-text foundation models","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530068"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3549201"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02711"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680664"},{"article-title":"Training deep neural-networks using a noise adaptation layer","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Goldberger","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472164"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0121"},{"key":"ref21","first-page":"5836","article-title":"Masking: A new perspective of noisy supervision","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS)","author":"Han"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2877939"},{"key":"ref23","first-page":"3763","article-title":"Robust inference via generative classifiers for handling noisy labels","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Lee"},{"key":"ref24","first-page":"8792","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS)","author":"Zhang"},{"key":"ref25","first-page":"15013","article-title":"Robust bi-tempered logistic loss based on bregman divergences","author":"Amid","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"Normalized loss functions for deep learning with noisy labels","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Ma","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref28","first-page":"10456","article-title":"Using trusted data to train deep networks on labels corrupted by severe noise","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS)","author":"Hendrycks"},{"article-title":"Are anchor points really indispensable in label-noise learning?","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS)","author":"Xia","key":"ref29"},{"article-title":"Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Jiang","key":"ref30"},{"key":"ref31","first-page":"960","article-title":"\"decoupling\u201d when to update\" from \"how to update\"","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS)","author":"Malach"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"article-title":"Dividemix: Learning with noisy labels as semi-supervised learning","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Li","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00945"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01420"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Yu","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00718"},{"article-title":"Unsupervised label noise modeling and loss correction","volume-title":"International Conference on Machine Learning (ICML)","author":"Arazo","key":"ref39"},{"article-title":"Early-learning regularization prevents memorization of noisy labels","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Liu","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00654"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00041"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01122"},{"key":"ref44","article-title":"Cifar-10 and cifar-100 datasets","volume-title":"University of Toronto, Tech. Rep.","author":"Krizhevsky","year":"2014"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"ref46","first-page":"5907","article-title":"Selfie: Refurbishing unclean samples for robust deep learning","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Song"},{"article-title":"Beyond synthetic noise: deep learning on controlled noisy labels","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Jiang","key":"ref47"},{"key":"ref48","article-title":"Webvision database: Visual learning and understanding from web data","volume-title":"Tech. Rep.","author":"Li","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00571"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Dosovitskiy","key":"ref50"},{"key":"ref51","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Song"},{"article-title":"Learning with feature-dependent label noise: A progressive approach","volume-title":"ICLR","author":"Zhang","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00302"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00232"},{"article-title":"Ssr: An efficient and robust framework for learning with unknown label noise","volume-title":"33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022","author":"Feng","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00013"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00935"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02152"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00519"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227884.pdf?arnumber=11227884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:33:47Z","timestamp":1763192027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227884\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227884","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}