{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T20:16:21Z","timestamp":1769285781827,"version":"3.49.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Junior Research Associate (JRA) program of RIKEN"},{"name":"Institute for AI and Beyond, UTokyo"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s10994-025-06966-z","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T17:28:45Z","timestamp":1769189325000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Weakly Supervised Classification with Pre-Trained Models: A Robust Fine-Tuning Approach"],"prefix":"10.1007","volume":"115","author":[{"given":"Ming","family":"Li","sequence":"first","affiliation":[]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"6966_CR1","doi-asserted-by":"crossref","unstructured":"Arazo, E., Ortego, D., Albert, P., O\u2019Connor, N.E., & McGuinness, K. (2020). Pseudo-labeling and confirmation bias in deep semi-supervised learning. In IJCNN","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"issue":"473","key":"6966_CR2","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1198\/016214505000000907","volume":"101","author":"PL Bartlett","year":"2006","unstructured":"Bartlett, P. L., Jordan, M. I., & McAuliffe, J. D. (2006). Convexity, classification, and risk bounds. Journal of the American Statistical Association,101(473), 138\u2013156.","journal-title":"Journal of the American Statistical Association"},{"key":"6966_CR3","unstructured":"Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. In NeurIPS"},{"key":"6966_CR5","unstructured":"Chen, H., Liu, F., Wang, Y., Zhao, L., v Wu, H. (2020). A variational approach for learning from positive and unlabeled data. In NeurIPS"},{"key":"6966_CR6","unstructured":"Chen, H., Wang, J., Feng, L., Li, X., Wang, Y., Xie, X., Sugiyama, M., Singh, R., & Raj, B. (2024). A general framework for learning from weak supervision. In ICML"},{"key":"6966_CR4","unstructured":"Chen, X., Chen, W., Chen, T., Yuan, Y., Gong, C., Chen, K., & Wang, Z. (2020). Self-PU: Self boosted and calibrated positive-unlabeled training. In ICML"},{"key":"6966_CR7","unstructured":"Chiang, C.-K., & Sugiyama, M. (2025). Unified risk analysis for weakly supervised learning. Transactions on Machine Learning Research"},{"key":"6966_CR8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR"},{"key":"6966_CR9","unstructured":"Fei-Fei, L., Fergus, R., & Perona, P. (2004). Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories. In CVPR workshop"},{"key":"6966_CR10","unstructured":"Feng, L., Lv, J., Han, B., Xu, M., Niu, G., Geng, X., An, B., & Sugiyama, M. (2020). Provably consistent partial-label learning. In NeurIPS"},{"key":"6966_CR11","unstructured":"Feng, L., Shu, S., Lu, N., Han, B., Xu, M., Niu, G., An, B., & Sugiyama, M. (2021). Pointwise binary classification with pairwise confidence comparisons. In ICML"},{"key":"6966_CR12","unstructured":"Gan, K., & Wei, T. (2024). Erasing the bias: Fine-tuning foundation models for semi-supervised learning. In ICML"},{"key":"6966_CR13","unstructured":"Garg, S., Wu, Y., Smola, A.J., Balakrishnan, S., & Lipton, Z.C. (2021). Mixture proportion estimation and PU learning: A modern approach. In NeurIPS"},{"key":"6966_CR14","unstructured":"Golowich, N., Rakhlin, A., & Shamir, O. (2018). Size-independent sample complexity of neural networks. In COLT"},{"key":"6966_CR15","unstructured":"Han, B., Yao, Q., Yu, X., Niu, G., Xu, M., Hu, W., Tsang, I., & Sugiyama, M. (2018). Co-teaching: Robust training of deep neural networks with extremely noisy labels. In NeurIPS"},{"issue":"7","key":"6966_CR16","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., & Borth, D. (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), 2217\u20132226.","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"6966_CR17","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015) Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531"},{"key":"6966_CR18","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B.-C., Cardie, C., Belongie, S., Hariharan, B., & Lim, S.-N. (2022). Visual prompt tuning. In ECCV","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"6966_CR19","unstructured":"Kiryo, R., Niu, G., Plessis, M.C., & Sugiyama, M. (2017). Positive-unlabeled learning with non-negative risk estimator. In NeurIPS"},{"key":"6966_CR20","volume-title":"Learning multiple layers of features from tiny images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky, A., & Hinton, G. E. (2009). Learning multiple layers of features from tiny images. Technical report, University of Toronto."},{"key":"6966_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, X., Fu, X., Zhang, X., Wang, W., Chen, S., & Yang, J. (2024). Promptkd: Unsupervised prompt distillation for vision-language models. In CVPR","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"6966_CR22","unstructured":"Lu, N., Niu, G., Menon, A.K., & Sugiyama, M. (2019). On the minimal supervision for training any binary classifier from only unlabeled data. In ICLR"},{"key":"6966_CR23","unstructured":"Lu, N., Zhang, T., Niu, G., & Sugiyama, M. (2020). Mitigating overfitting in supervised classification from two unlabeled datasets: A consistent risk correction approach. In AISTATS"},{"issue":"5","key":"6966_CR25","doi-asserted-by":"publisher","first-page":"2569","DOI":"10.1109\/TPAMI.2023.3275249","volume":"46","author":"J Lv","year":"2024","unstructured":"Lv, J., Liu, B., Feng, L., Xu, N., Xu, M., An, B., Niu, G., Geng, X., & Sugiyama, M. (2024). On the robustness of average losses for partial-label learning. IEEE Transactions on Pattern Analysis and Machine Intelligence,46(5), 2569\u20132583.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"6966_CR24","unstructured":"Lv, J., Xu, M., Feng, L., Niu, G., Geng, X., & Sugiyama, M. (2020). Progressive identification of true labels for partial-label learning. In ICML"},{"issue":"8","key":"6966_CR26","doi-asserted-by":"publisher","first-page":"3797","DOI":"10.1109\/TIT.2008.926323","volume":"54","author":"S Mendelson","year":"2008","unstructured":"Mendelson, S. (2008). Lower bounds for the empirical minimization algorithm. IEEE Transactions on Information Theory,54(8), 3797\u20133803.","journal-title":"IEEE Transactions on Information Theory"},{"key":"6966_CR27","unstructured":"Menon, A., Van\u00a0Rooyen, B., Ong, C.S., & Williamson, B. (2015). Learning from corrupted binary labels via class-probability estimation. In ICML"},{"key":"6966_CR28","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., & Jawahar, C. (2012). Cats and dogs. In CVPR","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"6966_CR29","unstructured":"Plessis, M., Niu, G., & Sugiyama, M. (2015). Convex formulation for learning from positive and unlabeled data. In ICML"},{"key":"6966_CR30","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In ICML"},{"key":"6966_CR31","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision,115, 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"6966_CR32","doi-asserted-by":"crossref","unstructured":"Shakeri, F., Huang, Y., Silva-Rodr\u00edguez, J., Bahig, H., Tang, A., Dolz, J., & Ben\u00a0Ayed, I. (2024). Few-shot adaptation of medical vision-language models. In MICCAI","DOI":"10.1007\/978-3-031-72390-2_52"},{"key":"6966_CR33","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019","volume-title":"Understanding machine learning: From theory to algorithms","author":"S Shalev-Shwartz","year":"2014","unstructured":"Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding machine learning: From theory to algorithms. Cambridge University Press."},{"key":"6966_CR34","unstructured":"Shukla, V., Zeng, Z., Ahmed, K., & Broeck, G. (2023). A unified approach to count-based weakly supervised learning. In NeurIPS"},{"key":"6966_CR35","unstructured":"Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C.A., Cubuk, E.D., Kurakin, A., & Li, C.-L. (2020). FixMatch: Simplifying semi-supervised learning with consistency and confidence. In NeurIPS"},{"key":"6966_CR36","doi-asserted-by":"crossref","unstructured":"Stevens, S., Wu, J., Thompson, M. J., Campolongo, E. G., Song, C. H., Carlyn, D. E., Dong, L., Dahdul, W. M., Stewart, C., Berger-Wolf, T., Chao, W. L. (2024). BIOCLIP: A vision foundation model for the tree of life. In CVPR","DOI":"10.1109\/CVPR52733.2024.01836"},{"key":"6966_CR37","volume-title":"Machine learning from weak supervision: An empirical risk minimization approach","author":"M Sugiyama","year":"2022","unstructured":"Sugiyama, M., Bao, H., Ishida, T., Lu, N., Sakai, T., & Niu, G. (2022). Machine learning from weak supervision: An empirical risk minimization approach. MIT Press."},{"key":"6966_CR38","unstructured":"Tarvainen, A., & Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In NeurIPS"},{"key":"6966_CR42","unstructured":"Wang, H.-H., Lin, W.-I., & Lin, H.-T. (2023a). CLCIFAR: CIFAR-derived benchmark datasets with human annotated complementary labels. arXiv preprint arXiv:2305.08295"},{"key":"6966_CR45","unstructured":"Wang, H., Xiao, R., Li, S., Feng, L., Niu, G., Chen, G., & Zhao, J. (2022) PiCO: Contrastive label disambiguation for partial label learning. In ICLR"},{"key":"6966_CR40","unstructured":"Wang, W., Feng, L., Jiang, Y., Niu, G., Zhang, M.-L., & Sugiyama, M. (2023b). Binary classification with confidence difference. In NeurIPS"},{"key":"6966_CR41","unstructured":"Wang, W., Ishida, T., Zhang, Y.-J., Niu, G., & Sugiyama, M. (2024). Learning with complementary labels revisited: The selected-completely-at-random setting is more practical. In ICML"},{"key":"6966_CR44","unstructured":"Wang, W., Wu, D.-D., Wang, J., Niu, G., Zhang, M.-L., & Sugiyama, M. (2025). Realistic evaluation of deep partial-label learning algorithms. In ICLR"},{"key":"6966_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., & Sun, J. (2022). MedCLIP: Contrastive learning from unpaired medical images and text. In EMNLP","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"issue":"1","key":"6966_CR46","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s11263-024-02192-7","volume":"133","author":"J Yang","year":"2025","unstructured":"Yang, J., Zhu, X., Bulat, A., Martinez, B., & Tzimiropoulos, G. (2025). Knowledge distillation meets open-set semi-supervised learning. International Journal of Computer Vision,133(1), 315\u2013334.","journal-title":"International Journal of Computer Vision"},{"key":"6966_CR47","doi-asserted-by":"crossref","unstructured":"Yao, H., Zhang, R., & Xu, C. (2023). Visual-language prompt tuning with knowledge-guided context optimization. In CVPR","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"6966_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., & Lu, H. (2018). Deep mutual learning. In CVPR","DOI":"10.1109\/CVPR.2018.00454"},{"key":"6966_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, B., Cui, Q., Song, R., Qiu, Y., & Liang, J. (2022a). Decoupled knowledge distillation. In CVPR","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"6966_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xu, Q., Jiang, Y., Wen, P., & Huang, Q. (2022b). Dist-PU: Positive-unlabeled learning from a label distribution perspective. In CVPR","DOI":"10.1109\/CVPR52688.2022.01406"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06966-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06966-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06966-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T06:02:17Z","timestamp":1769234537000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06966-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,23]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["6966"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06966-z","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,23]]},"assertion":[{"value":"11 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"28"}}