{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:55:37Z","timestamp":1781538937173,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810828","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"967-976","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Unveiling PEFT Robustness to Noisy Labels in VLMs: A Gradient-Loss Decoupling Perspective"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7179-897X","authenticated-orcid":false,"given":"Tengfei","family":"Ma","sequence":"first","affiliation":[{"name":"Huazhong University of Science and technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8524-6226","authenticated-orcid":false,"given":"Weiran","family":"Pan","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4488-0102","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"e_1_3_3_1_3_2","unstructured":"Guangyi Chen Weiran Yao Xiangchen Song Xinyue Li Yongming Rao and Kun Zhang. 2022. Plot: Prompt learning with optimal transport for vision-language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.01253 (2022)."},{"key":"e_1_3_3_1_4_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chen Guangyi","year":"2022","unstructured":"Guangyi Chen, Weiran Yao, Xiangchen Song, Xinyue Li, Yongming Rao, and Kun Zhang. 2022. PLOT: Prompt Learning with Optimal Transport for Vision-Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Shoufa Chen Chongjian Ge Zhan Tong Jiangliu Wang Yibing Song Jue Wang and Ping Luo. 2022. Adaptformer: Adapting vision transformers for scalable visual recognition. Advances in Neural Information Processing Systems 35 (2022) 16664\u201316678.","DOI":"10.52202\/068431-1212"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680664"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.5555\/3491440.3491745"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Peng Gao Shijie Geng Renrui Zhang Teli Ma Rongyao Fang Yongfeng Zhang Hongsheng Li and Yu Qiao. 2024. Clip-adapter: Better vision-language models with feature adapters. International Journal of Computer Vision 132 2 (2024) 581\u2013595.","DOI":"10.1007\/s11263-023-01891-x"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00562"},{"key":"e_1_3_3_1_12_2","volume-title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","author":"Gui Xian-Jin","year":"2021","unstructured":"Xian-Jin Gui, Wei Wang, and Zhang-Hao Tian. 2021. Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02711"},{"key":"e_1_3_3_1_14_2","unstructured":"Bo Han Quanming Yao Xingrui Yu Gang Niu Miao Xu Weihua Hu Ivor Tsang and Masashi Sugiyama. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Patrick Helber Benjamin Bischke Andreas Dengel and Damian Borth. 2019. Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 12 7 (2019) 2217\u20132226.","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"e_1_3_3_1_16_2","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et\u00a0al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1 2 (2022) 3."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00463"},{"key":"e_1_3_3_1_18_2","first-page":"4904","volume-title":"International conference on machine learning","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904\u20134916."},{"key":"e_1_3_3_1_19_2","first-page":"2304","volume-title":"International conference on machine learning","author":"Jiang Lu","year":"2018","unstructured":"Lu Jiang, Zhengyuan Zhou, Thomas Leung, Li-Jia Li, and Li Fei-Fei. 2018. Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In International conference on machine learning. PMLR, 2304\u20132313."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_3_1_21_2","first-page":"3488","volume-title":"International conference on machine learning","author":"Konstantinov Nikola","year":"2019","unstructured":"Nikola Konstantinov and Christoph Lampert. 2019. Robust learning from untrusted sources. In International conference on machine learning. PMLR, 3488\u20133498."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00571"},{"key":"e_1_3_3_1_24_2","volume-title":"International Conference on Learning Representations","author":"Li Junnan","year":"2020","unstructured":"Junnan Li, Richard Socher, and Steven\u00a0CH Hoi. 2020. DivideMix: Learning with Noisy Labels as Semi-supervised Learning. In International Conference on Learning Representations."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.797"},{"key":"e_1_3_3_1_27_2","unstructured":"Wen Li Limin Wang Wei Li Eirikur Agustsson and Luc Van\u00a0Gool. 2017. Webvision database: Visual learning and understanding from web data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1708.02862 (2017)."},{"key":"e_1_3_3_1_28_2","unstructured":"Sheng Liu Jonathan Niles-Weed Narges Razavian and Carlos Fernandez-Granda. 2020. Early-learning regularization prevents memorization of noisy labels. Advances in neural information processing systems 33 (2020) 20331\u201320342."},{"key":"e_1_3_3_1_29_2","first-page":"6543","volume-title":"International conference on machine learning","author":"Ma Xingjun","year":"2020","unstructured":"Xingjun Ma, Hanxun Huang, Yisen Wang, Simone Romano, Sarah Erfani, and James Bailey. 2020. Normalized loss functions for deep learning with noisy labels. In International conference on machine learning. PMLR, 6543\u20136553."},{"key":"e_1_3_3_1_30_2","unstructured":"Subhransu Maji Esa Rahtu Juho Kannala Matthew Blaschko and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1306.5151 (2013)."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02722"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01859"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Yuxin Peng Yunzhen Zhao and Junchao Zhang. 2018. Two-stream collaborative learning with spatial-temporal attention for video classification. IEEE Transactions on Circuits and Systems for Video Technology3 (2018) 773\u2013786.","DOI":"10.1109\/TCSVT.2018.2808685"},{"key":"e_1_3_3_1_36_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02235"},{"key":"e_1_3_3_1_38_2","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Wang Haoyu","year":"2024","unstructured":"Haoyu Wang, Zhuo Huang, Zhiwei Lin, and Tongliang Liu. 2024. Noisegpt: Label noise detection and rectification through probability curvature. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Tong Wei Hao-Tian Li ChunShu Li Jiang-Xin Shi Yu-Feng Li and Min-Ling Zhang. 2024. Vision-Language Models are Strong Noisy Label Detectors. Advances in Neural Information Processing Systems 37 (2024) 58154\u201358173.","DOI":"10.52202\/079017-1854"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01420"},{"key":"e_1_3_3_1_43_2","unstructured":"Xiaobo Xia Tongliang Liu Bo Han Nannan Wang Mingming Gong Haifeng Liu Gang Niu Dacheng Tao and Masashi Sugiyama. 2020. Part-dependent label noise: Towards instance-dependent label noise. Advances in Neural Information Processing Systems 33 (2020) 7597\u20137610."},{"key":"e_1_3_3_1_44_2","first-page":"2691","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Xiao Tong","year":"2015","unstructured":"Tong Xiao, Tian Xia, Yi Yang, Chang Huang, and Xiaogang Wang. 2015. Learning from massive noisy labeled data for image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2691\u20132699."},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Xichen Ye Xiaoqiang Li Tong Liu Yan Sun Weiqin Tong et\u00a0al. 2023. Active negative loss functions for learning with noisy labels. Advances in Neural Information Processing Systems 36 (2023) 6917\u20136940.","DOI":"10.52202\/075280-0303"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"e_1_3_3_1_47_2","unstructured":"Elad\u00a0Ben Zaken Shauli Ravfogel and Yoav Goldberg. 2021. Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.10199 (2021)."},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00166"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"crossref","unstructured":"Maxime Zanella Beno\u00eet G\u00e9rin and Ismail Ayed. 2024. Boosting vision-language models with transduction. Advances in Neural Information Processing Systems 37 (2024) 62223\u201362256.","DOI":"10.52202\/079017-1988"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_3_1_51_2","volume-title":"International Conference on Learning Representations","author":"Zhang Chiyuan","year":"2017","unstructured":"Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. 2017. Understanding deep learning requires rethinking generalization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Sy8gdB9xx"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00315"},{"key":"e_1_3_3_1_54_2","unstructured":"Zhilu Zhang and Mert Sabuncu. 2018. Generalized cross entropy loss for training deep neural networks with noisy labels. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"crossref","unstructured":"Kaiyang Zhou Jingkang Yang Chen\u00a0Change Loy and Ziwei Liu. 2022. Learning to prompt for vision-language models. International Journal of Computer Vision 130 9 (2022) 2337\u20132348.","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:24:27Z","timestamp":1781537067000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":55,"alternative-id":["10.1145\/3805622.3810828","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810828","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}