{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T09:12:32Z","timestamp":1773220352817,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T00:00:00Z","timestamp":1679961600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T00:00:00Z","timestamp":1679961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001774","name":"University of Sydney","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001774","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2024,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deep models trained by using clean data have achieved tremendous success in fine-grained image classification. Yet, they generally suffer from significant performance degradation when encountering noisy labels. Existing approaches to handle label noise, though proved to be effective for generic object recognition, usually fail on fine-grained data. The reason is that, on fine-grained data, the category difference is subtle and the training sample size is small. Then deep models could easily overfit the noisy labels. To improve the robustness of deep models on noisy data for fine-grained visual categorization, in this paper, we propose a novel learning framework named ProtoSimi. Our method employs an adaptive label correction strategy, ensuring effective learning on limited data. Specifically, our approach considers the criteria of exploring the effectiveness of both global class-prototype and part class-prototype similarities in identifying and correcting labels of samples. We evaluate our method on three standard benchmarks of fine-grained recognition. Experimental results show that our method outperforms the existing label noisy methods by a large margin. In ablation studies, we also verify that our method is non-sensitive to hyper-parameters selection and can be integrated with other FGVC methods to increase the generalization performance.<\/jats:p>","DOI":"10.1007\/s10994-023-06313-0","type":"journal-article","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T19:02:54Z","timestamp":1680030174000},"page":"1903-1920","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["ProtoSimi: label correction for fine-grained visual categorization"],"prefix":"10.1007","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7475-5770","authenticated-orcid":false,"given":"Jialiang","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoli","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruxing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,28]]},"reference":[{"key":"6313_CR1","unstructured":"Arpit, D., Jastrzebski, S. L., Ballas, N., Krueger, D., Bengio, E., Kanwal, M. S. et al. (2017). A closer look at memorization in deep networks. In ICML (pp. 233\u2013242)."},{"key":"6313_CR2","first-page":"24392","volume":"34","author":"Y Bai","year":"2021","unstructured":"Bai, Y., Yang, E., Han, B., Yang, Y., Li, J., Mao, Y., Niu, G., & Liu, T. (2021). Understanding and improving early stopping for learning with noisy labels. Advances in Neural Information Processing Systems, 34, 24392\u201324403.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6313_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bai, Y., Zhang, W., & Mei, T. (2019). Destruction and construction learning for fine-grained image recognition. In CVPR (pp. 5157\u20135166).","DOI":"10.1109\/CVPR.2019.00530"},{"key":"6313_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In CVPR (pp. 248\u2013255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6313_CR5","unstructured":"Foret, P., Kleiner, A., Mobahi, H., & Neyshabur, B. (2020). Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv:2010.01412"},{"issue":"3","key":"6313_CR6","doi-asserted-by":"publisher","first-page":"2835","DOI":"10.1109\/TPAMI.2022.3178690","volume":"45","author":"C Gong","year":"2023","unstructured":"Gong, C., Ding, Y., Han, B., Niu, G., Yang, J., You, J., Tao, D., Sugiyama, M. (2023).\nClass-wise denoising for robust learning under label noise. IEEE Transactions\non Pattern Analysis and Machine Intelligence, 45(3), 2835\u20132848. https:\/\/doi.org\/10.1109\/TPAMI.2022.3178690","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"6313_CR7","unstructured":"Han, B., Yao, Q., Yu, X., Niu, G., Xu, M., Hu, W., & Sugiyama, M. (2018). Co-teaching: Robust training of deep neural networks with extremely noisy labels. In NeurIPS (pp. 8527\u20138537)."},{"key":"6313_CR8","doi-asserted-by":"crossref","unstructured":"Han, J., Luo, P., & Wang, X. (2019). Deep self-learning from noisy labels. In ICCV (pp. 5138\u20135147).","DOI":"10.1109\/ICCV.2019.00524"},{"key":"6313_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J.(2016). Deep residual learning for image recognition. In CVPR (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"6313_CR10","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1109\/TCSVT.2021.3065693","volume":"32","author":"H Huang","year":"2022","unstructured":"Huang, H., Zhang, J., Yu, L., Zhang, J., Wu, Q., & Xu, C. (2022). TOAN: Target-oriented alignment network for fine-grained image categorization with few labeled samples. IEEE Transactions on Circuits and Systems for Video Technology, 32(2), 853\u2013866. https:\/\/doi.org\/10.1109\/TCSVT.2021.3065693","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"6313_CR11","unstructured":"Huang, L., Zhang, C., & Zhang, H. (2020). Self-adaptive training: Beyond empirical risk minimization. In NeurIPS (Vol.\u00a033)."},{"key":"6313_CR12","doi-asserted-by":"crossref","unstructured":"Huang, S., Xu, Z., Tao, D., & Zhang, Y. (2016) . Part-stacked CNN for fine-grained visual categorization. In CVPR (pp. 1173\u20131182).","DOI":"10.1109\/CVPR.2016.132"},{"key":"6313_CR13","unstructured":"Jiang, L., Zhou, Z., Leung, T., Li, L.-J., & Fei-Fei, L. (2018). Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In ICML (pp. 2304\u20132313)."},{"key":"6313_CR14","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., & Fei-Fei, L. (2013). 3D object representations for fine-grained categorization. In ICCVW (pp. 554\u2013561).","DOI":"10.1109\/ICCVW.2013.77"},{"key":"6313_CR15","doi-asserted-by":"crossref","unstructured":"Lee, K.-H., He, X., Zhang, L., & Yang, L. (2018). Cleannet: Transfer learning for scalable image classifier training with label noise. In CVPR.","DOI":"10.1109\/CVPR.2018.00571"},{"key":"6313_CR16","unstructured":"Li, J., Socher, R., & Hoi, S. C. (2020). Dividemix: Learning with noisy labels as semi-supervised learning. In ICLR."},{"key":"6313_CR17","unstructured":"Li, X., Liu, T., Han, B., Niu, G., & Sugiyama, M. (2021). Provably end-to-end label-noise learning without anchor points. In International conference on machine learning (pp. 6403\u20136413)."},{"key":"6313_CR18","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhang, C., Yao, Y., Wei, X., Shen, F., Zhang, J., & Tang, Z. (2021). Exploiting web images for fine-grained visual recognition by eliminating noisy samples and utilizing hard ones.","DOI":"10.1109\/TMM.2021.3055024"},{"key":"6313_CR19","unstructured":"Liu, S., Niles-Weed, J., Razavian, N., Fernandez-Granda, C. (2020). Early-learning regularization prevents memorization of noisy labels. In NeurIPS (Vol. 33)."},{"issue":"34","key":"6313_CR20","first-page":"47","volume":"38","author":"T Liu","year":"2015","unstructured":"Liu, T., & Tao, D. (2015). Classification with noisy labels by importance reweighting. TPAMI, 38(34), 47\u2013461.","journal-title":"TPAMI"},{"key":"6313_CR21","unstructured":"Maji, S., Kannala, J., Rahtu, E., Blaschko, M., & Vedaldi, A. (2013). Fine-grained visual classification of aircraft (Technical Report)."},{"key":"6313_CR22","unstructured":"Malach, E. & Shalev-Shwartz, S. (2017). Decoupling \u201cwhen to update\u201d from \u201chow to update\u201d. arXiv preprint arXiv:1706.02613"},{"key":"6313_CR23","doi-asserted-by":"crossref","unstructured":"Patrini, G., Rozza, A., Krishna\u00a0Menon, A., Nock, R., & Qu, L. (2017). Making deep neural networks robust to label noise: A loss correction approach. In CVPR (pp. 1944\u20131952).","DOI":"10.1109\/CVPR.2017.240"},{"key":"6313_CR24","unstructured":"Song, H., Kim, M., & Lee, J.-G. (2019). Selfie: Refurbishing unclean samples for robust deep learning. In ICML (pp. 5907\u20135915)."},{"key":"6313_CR25","doi-asserted-by":"crossref","unstructured":"Sun, M., Yuan, Y., Zhou, F., & Ding, E. (2018). Multi-attention multi-class constraint for fine-grained image recognition. In European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"6313_CR26","doi-asserted-by":"crossref","unstructured":"Sun, Z., Yao, Y., Wei, X.-S., Zhang, Y., Shen, F., Wu, J., & Shen, H. T. (2021) . Webly supervised fine-grained recognition: benchmark datasets and an approach. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10602\u201310611).","DOI":"10.1109\/ICCV48922.2021.01043"},{"key":"6313_CR27","unstructured":"Van\u00a0der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research, 9(11)."},{"key":"6313_CR28","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., & Belongie, S. (2011). The Caltech-UCSD Birds-200-2011 Dataset (Technical Report No CNS-TR-2011-00). California Institute of Technology."},{"key":"6313_CR29","doi-asserted-by":"crossref","unstructured":"Wei, H., Feng, L., Chen, X., & An, B. (2020). Combating noisy labels by agreement: A joint training method with co-regularization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13726\u201313735).","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"6313_CR30","unstructured":"Xia, X., Liu, T., Han, B., Gong, C., Wang, N., Ge, Z., & Chang, Y. (2021). Robust early-learning: Hindering the memorization of noisy labels. In International conference on learning representations."},{"key":"6313_CR31","doi-asserted-by":"crossref","unstructured":"Yang, M., Huang, Z., Hu, P., Li, T., Lv, J., & Peng, X. (2022). Learning with twin noisy labels for visible-infrared person re-identification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14308\u201314317).","DOI":"10.1109\/CVPR52688.2022.01391"},{"key":"6313_CR32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155499","author":"M Yang","year":"2022","unstructured":"Yang, M., Li, Y., Hu, P., Bai, J., Lv, J. C., & Peng, X. (2022). Robust multi-view clustering with incomplete information. IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2022.3155499","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"6313_CR33","doi-asserted-by":"crossref","unstructured":"Yang, M., Li, Y., Huang, Z., Liu, Z., Hu, P., & Peng, X. (2021). Partially view-aligned representation learning with noise-robust contrastive loss. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 1134\u20131143).","DOI":"10.1109\/CVPR46437.2021.00119"},{"key":"6313_CR34","unstructured":"Yao, Y., Liu, T., Han, B., Gong, M., Deng, J., Niu, G., & Sugiyama, M.(2020) . Dual t: Reducing estimation error for transition matrix in label-noise learning."},{"key":"6313_CR35","unstructured":"Yu, X., Han, B., Yao, J., Niu, G., Tsang, I. W., & Sugiyama, M. (2019). How does disagreement help generalization against label corruption? arXiv preprint arXiv:1901.04215"},{"key":"6313_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, C., Yao, Y., Shu, X., Li, Z., Tang, Z., & Wu, Q. (2020). Data-driven meta-set based fine-grained visual classification. arXiv preprint arXiv:2008.02438","DOI":"10.1145\/3394171.3414044"},{"key":"6313_CR37","unstructured":"Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412"},{"key":"6313_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, L., Huang, S., Liu, W., & Tao, D. (2019). Learning a mixture of granularity-specific experts for fine-grained categorization. In ICCV (pp. 8331\u20138340).","DOI":"10.1109\/ICCV.2019.00842"},{"key":"6313_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, X., Xiong, H., Zhou, W., Lin, W., & Tian, Q. (2016). Picking deep filter responses for fine-grained image recognition. In CVPR (pp. 1134\u20131142).","DOI":"10.1109\/CVPR.2016.128"},{"key":"6313_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Mei, T., & Luo, J. (2017). Learning multi-attention convolutional neural network for fine-grained image recognition. In ICCV (pp. 5209\u20135217).","DOI":"10.1109\/ICCV.2017.557"},{"key":"6313_CR41","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Zha, Z.-J., & Luo, J. (2019). Looking for the devil in the details: Learning trilinear attention sampling network for fine-grained image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5012\u20135021).","DOI":"10.1109\/CVPR.2019.00515"},{"key":"6313_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In CVPR (pp. 2921\u20132929).","DOI":"10.1109\/CVPR.2016.319"},{"key":"6313_CR43","doi-asserted-by":"crossref","unstructured":"Zhuang, P., Wang, Y., & Qiao, Y. (2020). Learning attentive pairwise interaction for fine-grained classification. In AAAI (pp. 13130\u201313137).","DOI":"10.1609\/aaai.v34i07.7016"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06313-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06313-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06313-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T17:14:26Z","timestamp":1711646066000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06313-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,28]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["6313"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06313-0","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,28]]},"assertion":[{"value":"14 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}