{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T05:05:45Z","timestamp":1764997545680,"version":"3.37.3"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG-RP-2019-015"],"award-info":[{"award-number":["AISG-RP-2019-015"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,11]]},"abstract":"Abstract<\/jats:title>Web image datasets curated online inherently contain ambiguous in-distribution instances and out-of-distribution instances, which we collectively callnon-conforming<\/jats:italic>(NC) instances. In many recent approaches for mitigating the negative effects of NC instances, the core implicit assumption is that the NC instances can be found via entropy maximization. For \u201centropy\u201d to be well-defined, we are interpreting the output prediction vector of an instance as the parameter vector of a multinomial random variable, with respect to some trained model with a softmax output layer. Hence, entropy maximization is based on the idealized assumption that NC instances have predictions that are \u201calmost\u201d uniformly distributed. However, in real-world web image datasets, there are numerous NC instances whose predictions are far from being uniformly distributed. To tackle the limitation of entropy maximization, we propose$$(\\alpha , \\beta )$$<\/jats:tex-math>(<\/mml:mo>\u03b1<\/mml:mi>,<\/mml:mo>\u03b2<\/mml:mi>)<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>-generalized KL divergence,$${\\mathcal {D}}_{\\text {KL}}^{\\alpha , \\beta }(p\\Vert q)$$<\/jats:tex-math>D<\/mml:mi>KL<\/mml:mtext><\/mml:mrow>\u03b1<\/mml:mi>,<\/mml:mo>\u03b2<\/mml:mi><\/mml:mrow><\/mml:msubsup>(<\/mml:mo>p<\/mml:mi>\u2016<\/mml:mo>q<\/mml:mi>)<\/mml:mo><\/mml:mrow><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>, which can be used to identify significantly more NC instances. Theoretical properties of$${\\mathcal {D}}_{\\text {KL}}^{\\alpha , \\beta }(p\\Vert q)$$<\/jats:tex-math>D<\/mml:mi>KL<\/mml:mtext><\/mml:mrow>\u03b1<\/mml:mi>,<\/mml:mo>\u03b2<\/mml:mi><\/mml:mrow><\/mml:msubsup>(<\/mml:mo>p<\/mml:mi>\u2016<\/mml:mo>q<\/mml:mi>)<\/mml:mo><\/mml:mrow><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>are proven, and we also show empirically that a simple use of$${\\mathcal {D}}_{\\text {KL}}^{\\alpha , \\beta }(p\\Vert q)$$<\/jats:tex-math>D<\/mml:mi>KL<\/mml:mtext><\/mml:mrow>\u03b1<\/mml:mi>,<\/mml:mo>\u03b2<\/mml:mi><\/mml:mrow><\/mml:msubsup>(<\/mml:mo>p<\/mml:mi>\u2016<\/mml:mo>q<\/mml:mi>)<\/mml:mo><\/mml:mrow><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>outperforms all baselines on the NC instance identification task. Building upon$$(\\alpha ,\\beta )$$<\/jats:tex-math>(<\/mml:mo>\u03b1<\/mml:mi>,<\/mml:mo>\u03b2<\/mml:mi>)<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>-generalized KL divergence, we also introduce a new iterative training framework,GenKL<\/jats:sc>, that identifies and relabels NC instances. When evaluated on three web image datasets, Clothing1M, Food101\/Food101N, and mini WebVision 1.0, we achieved new state-of-the-art classification accuracies:$$81.34\\%$$<\/jats:tex-math>81.34<\/mml:mn>%<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>,$$85.73\\%$$<\/jats:tex-math>85.73<\/mml:mn>%<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>and$$78.99\\%$$<\/jats:tex-math>78.99<\/mml:mn>%<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>\/$$92.54\\%$$<\/jats:tex-math>92.54<\/mml:mn>%<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>(top-1\/top-5), respectively.<\/jats:p>","DOI":"10.1007\/s11263-023-01815-9","type":"journal-article","created":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T12:01:31Z","timestamp":1689422491000},"page":"3035-3059","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence"],"prefix":"10.1007","volume":"131","author":[{"given":"Xia","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5568-7610","authenticated-orcid":false,"given":"Kai Fong Ernest","family":"Chong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,15]]},"reference":[{"key":"1815_CR1","doi-asserted-by":"crossref","unstructured":"Albert, P., Ortego, D., Arazo, E., O\u2019Connor, N.E., & McGuinness, K. (2022) Addressing out-of-distribution label noise in Webly\u2013Labelled data. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (pp. 392\u2013401).","DOI":"10.1109\/WACV51458.2022.00245"},{"key":"1815_CR2","unstructured":"Arpit, D., Jastrz\u0119bski, S., Ballas, N., Krueger, D., Bengio, E., Kanwal, M.S., Maharaj, T., Fischer, A., Courville, A., & Bengio, Y. (2017). A closer look at memorization in deep networks. In International conference on machine learning (pp. 233\u2013242). PMLR."},{"key":"1815_CR3","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., & Gool, L.V. (2014). Food-101\u2013mining discriminative components with random forests. In European conference on computer vision (pp. 446\u2013461). Springer.","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"1815_CR4","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., & Van\u00a0Gool, L. (2014) Food-101\u2014mining discriminative components with random forests. In European conference on computer vision","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"1815_CR5","doi-asserted-by":"crossref","unstructured":"Chan, R., Rottmann, M., & Gottschalk, H. (2021). Entropy maximization and meta classification for out-of-distribution detection in semantic segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 5128\u20135137).","DOI":"10.1109\/ICCV48922.2021.00508"},{"issue":"5","key":"1815_CR6","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1080\/00207390500063967","volume":"36","author":"M Feuerman","year":"2005","unstructured":"Feuerman, M., & Miller, A. (2005). The kappa statistic as a function of sensitivity and specificity. International Journal of Mathematical Education in Science and Technology, 36(5), 517\u2013527.","journal-title":"International Journal of Mathematical Education in Science and Technology"},{"key":"1815_CR7","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Kumar, H., & Sastry, P. (2017) Robust loss functions under label noise for deep neural networks. In Proceedings of the AAAI conference on artificial intelligence (vol. 31).","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"1815_CR8","unstructured":"Goldberger, J., & Ben-Reuven, E. (2016) Training deep neural-networks using a noise adaptation layer"},{"key":"1815_CR9","doi-asserted-by":"crossref","unstructured":"Guo, S., Huang, W., Zhang, H., Zhuang, C., Dong, D., Scott, M.R., & Huang, D. (2018) Curriculumnet: Weakly supervised learning from large-scale web images. In Proceedings of the European conference on computer vision (ECCV) (pp. 135\u2013150).","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"1815_CR10","doi-asserted-by":"crossref","unstructured":"Han, J., Luo, P., & Wang, X. (2019) Deep self-learning from noisy labels. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 5138\u20135147).","DOI":"10.1109\/ICCV.2019.00524"},{"key":"1815_CR11","unstructured":"Han, B., Yao, Q., Liu, T., Niu, G., Tsang, I.W., Kwok, J.T., & Sugiyama, M. (2020) A survey of label-noise representation learning: Past, present and future. arXiv preprint arXiv:2011.04406"},{"key":"1815_CR12","unstructured":"Han, B., Yao, J., Niu, G., Zhou, M., Tsang, I., Zhang, Y., & Sugiyama, M. (2018) Masking: A new perspective of noisy supervision. Advances in Neural Information Processing Systems 31"},{"key":"1815_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"issue":"5","key":"1815_CR14","doi-asserted-by":"publisher","first-page":"114","DOI":"10.3390\/fi13050114","volume":"13","author":"S Helmstetter","year":"2021","unstructured":"Helmstetter, S., & Paulheim, H. (2021). Collecting a large scale dataset for classifying fake news tweets using weak supervision. Future Internet, 13(5), 114.","journal-title":"Future Internet"},{"key":"1815_CR15","unstructured":"Hendrycks, D., Mazeika, M., Wilson, D., & Gimpel, K. (2018) Using trusted data to train deep networks on labels corrupted by severe noise. Advances in Neural Information Processing Systems 31"},{"key":"1815_CR16","unstructured":"Ioffe, S., & Szegedy, C. (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (pp. 448\u2013456). PMLR."},{"key":"1815_CR17","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198503682.001.0001","volume-title":"The theory of probability","author":"H Jeffreys","year":"1998","unstructured":"Jeffreys, H. (1998). The theory of probability. Oxford: OUP Oxford."},{"key":"1815_CR18","doi-asserted-by":"crossref","unstructured":"Jenni, S., & Favaro, P. (2018) Deep bilevel learning. In Proceedings of the European conference on computer vision (ECCV), pp. 618\u2013633","DOI":"10.1007\/978-3-030-01249-6_38"},{"key":"1815_CR19","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 International conference on machine learning (pp. 2304\u20132313). PMLR"},{"key":"1815_CR20","unstructured":"Kaur, P., Sikka, K., & Divakaran, A. (2017). Combining weakly and webly supervised learning for classifying food images. arXiv preprint arXiv:1712.08730"},{"key":"1815_CR21","unstructured":"Kirsch, A., Mukhoti, J., van Amersfoort, J., Torr, P. H. S., & Gal, Y. (2021). On Pitfalls in OoD Detection: Entropy Considered Harmful. ICML: Uncertainty Robustness in Deep Learning Workshop."},{"issue":"6","key":"1815_CR22","doi-asserted-by":"publisher","first-page":"2331","DOI":"10.1109\/TCYB.2018.2825353","volume":"49","author":"J Kittler","year":"2018","unstructured":"Kittler, J., & Zor, C. (2018). Delta divergence: A novel decision cognizant measure of classifier incongruence. IEEE Transactions on Cybernetics, 49(6), 2331\u20132343.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"1815_CR23","unstructured":"Krogh, A., & Hertz, J. (1991) A simple weight decay can improve generalization. Advances in Neural Information Processing Systems 4"},{"key":"1815_CR24","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 Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5447\u20135456).","DOI":"10.1109\/CVPR.2018.00571"},{"key":"1815_CR25","unstructured":"Li, J., Socher, R., & Hoi, S.C.(2020). Dividemix: Learning with noisy labels as semi-supervised learning. arXiv preprint arXiv:2002.07394."},{"key":"1815_CR26","unstructured":"Li, W., Wang, L., Li, W., Agustsson, E., & Gool, L.V. (2017) Webvision database: Visual learning and understanding from web data. CoRR"},{"key":"1815_CR27","unstructured":"Li, J., Xiong, C., & Hoi, S.C.H. (2021) Mopro: Webly supervised learning with momentum prototypes. ICLR"},{"key":"1815_CR28","doi-asserted-by":"crossref","unstructured":"Liang, C., Yu, Y., Jiang, H., Er, S., Wang, R., Zhao, T., & Zhang, C. (2020) Bond: Bert-assisted open-domain named entity recognition with distant supervision. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 1054\u20131064).","DOI":"10.1145\/3394486.3403149"},{"issue":"1","key":"1815_CR29","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/18.61115","volume":"37","author":"J Lin","year":"1991","unstructured":"Lin, J. (1991). Divergence measures based on the Shannon entropy. IEEE Transactions on Information Theory, 37(1), 145\u2013151.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"5","key":"1815_CR30","doi-asserted-by":"publisher","first-page":"1808","DOI":"10.1109\/TPAMI.2019.2961910","volume":"43","author":"J Li","year":"2019","unstructured":"Li, J., Song, Y., Zhu, J., Cheng, L., Su, Y., Ye, L., Yuan, P., & Han, S. (2019). Learning from large-scale noisy web data with ubiquitous reweighting for image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(5), 1808\u20131814.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"1815_CR31","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietik\u00e4inen, M. (2020). Deep learning for generic object detection: A survey. International Journal of Computer Vision, 128(2), 261\u2013318.","journal-title":"International Journal of Computer Vision"},{"key":"1815_CR32","unstructured":"Lyu, Y., & Tsang, I.W. (2019) Curriculum loss: Robust learning and generalization against label corruption. arXiv preprint arXiv:1905.10045"},{"key":"1815_CR33","unstructured":"Ma, X., Huang, H., Wang, Y., Romano, S., Erfani, S., Bailey, J. (2020) Normalized loss functions for deep learning with noisy labels. In International conference on machine learning (pp. 6543\u20136553). PMLR"},{"key":"1815_CR34","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S., Anwer, R.M., & Yang, M.-H. (2022). Class-agnostic object detection with multi-modal transformer. In European conference on computer vision (pp. 512\u2013531). Springer.","DOI":"10.1007\/978-3-031-20080-9_30"},{"key":"1815_CR35","unstructured":"Mac\u00eado, D., & Ludermir, T. (2021) Enhanced isotropy maximization loss: Seamless and high-performance out-of-distribution detection simply replacing the softmax loss. arXiv preprint arXiv:2105.14399"},{"key":"1815_CR36","doi-asserted-by":"publisher","unstructured":"Mac\u00eado, D., Ren, T.I., Zanchettin, C., Oliveira, A.L.I., & Ludermir, T. (2021) Entropic out-of-distribution detection. In 2021 International Joint Conference on Neural Networks (IJCNN) (pp. 1\u20138). https:\/\/doi.org\/10.1109\/IJCNN52387.2021.9533899.","DOI":"10.1109\/IJCNN52387.2021.9533899"},{"key":"1815_CR37","doi-asserted-by":"crossref","unstructured":"Mac\u00eado, D., Ren, T.I., Zanchettin, C., Oliveira, A.L., & Ludermir, T. (2021) Entropic out-of-distribution detection. In 2021 international joint conference on neural networks (IJCNN) (pp. 1\u20138. IEEE).","DOI":"10.1109\/IJCNN52387.2021.9533899"},{"key":"1815_CR38","unstructured":"MacKay, D. J. C. (2003). Information Theory, Inference and Learning Algorithms. Cambridge University Press."},{"key":"1815_CR39","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 Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1944\u20131952).","DOI":"10.1109\/CVPR.2017.240"},{"key":"1815_CR40","doi-asserted-by":"crossref","unstructured":"Peng, X., Wang, K., Zeng, Z., Li, Q., Yang, J., & Qiao, Y. (2020) Suppressing mislabeled data via grouping and self-attention. In European conference on computer vision (pp. 786\u2013802. Springer.","DOI":"10.1007\/978-3-030-58517-4_46"},{"key":"1815_CR41","unstructured":"Pereyra, G., Tucker, G., Chorowski, J., Kaiser, \u0141., & Hinton, G. (2017) Regularizing neural networks by penalizing confident output distributions. arXiv preprint arXiv:1701.06548"},{"key":"1815_CR42","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1016\/j.patcog.2016.08.018","volume":"61","author":"M Ponti","year":"2017","unstructured":"Ponti, M., Kittler, J., Riva, M., de Campos, T., & Zor, C. (2017). A decision cognizant Kullback\u2013Leibler divergence. Pattern Recognition, 61, 470\u2013478.","journal-title":"Pattern Recognition"},{"key":"1815_CR43","doi-asserted-by":"crossref","unstructured":"Shang, J., Liu, L., Ren, X., Gu, X., Ren, T., & Han, J. (2018). Learning named entity tagger using domain-specific dictionary. arXiv preprint arXiv:1809.03599","DOI":"10.18653\/v1\/D18-1230"},{"key":"1815_CR44","doi-asserted-by":"crossref","unstructured":"Sharma, K., Donmez, P., Luo, E., Liu, Y., & Yalniz, I.Z. (2020) Noiserank: Unsupervised label noise reduction with dependence models. In European conference on computer vision (pp. 737\u2013753). Springer","DOI":"10.1007\/978-3-030-58583-9_44"},{"issue":"1","key":"1815_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 1\u201348.","journal-title":"Journal of Big Data"},{"key":"1815_CR46","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/0024-3795(92)90321-Z","volume":"177","author":"RL Smith","year":"1992","unstructured":"Smith, R. L. (1992). Some interlacing properties of the Schur complement of a Hermitian matrix. Linear Algebra Appl., 177, 137\u2013144.","journal-title":"Linear Algebra Appl."},{"key":"1815_CR47","unstructured":"Song, H., Kim, M., & Lee, J.-G. (2019) Selfie: Refurbishing unclean samples for robust deep learning. In International Conference on Machine Learning (pp. 5907\u20135915). PMLR."},{"issue":"1","key":"1815_CR48","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1), 1929\u20131958.","journal-title":"The Journal of Machine Learning Research"},{"key":"1815_CR49","unstructured":"Sukhbaatar, S., & Fergus, R. (2014) Learning from noisy labels with deep neural networks. arXiv preprint arXiv:1406.2080"},{"key":"1815_CR50","doi-asserted-by":"crossref","unstructured":"Tanaka, D., Ikami, D., Yamasaki, T., & Aizawa, K. (2018) Joint optimization framework for learning with noisy labels. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5552\u20135560).","DOI":"10.1109\/CVPR.2018.00582"},{"key":"1815_CR51","doi-asserted-by":"crossref","unstructured":"Tekumalla, R., & Banda, J.M. (2021) Using weak supervision to generate training datasets from social media data: a proof of concept to identify drug mentions. Neural Computing and Applications (pp. 1\u20139).","DOI":"10.1007\/s00521-021-06614-2"},{"key":"1815_CR52","volume-title":"Elements of information theory","author":"M Thomas","year":"2006","unstructured":"Thomas, M., & Joy, A. T. (2006). Elements of information theory. Wiley-Interscience."},{"key":"1815_CR53","doi-asserted-by":"crossref","unstructured":"Tu, Y., Niu, L., Chen, J., Cheng, D., & Zhang, L. (2020). Learning from web data with self-organizing memory module. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12846\u201312855).","DOI":"10.1109\/CVPR42600.2020.01286"},{"key":"1815_CR54","doi-asserted-by":"crossref","unstructured":"Varma, P., & R\u00e9, C. (2018). Snuba: Automating weak supervision to label training data. In Proceedings Of The Vldb Endowment. International Conference On Very Large Data Bases (vol. 12, p. 223). NIH Public Access.","DOI":"10.14778\/3291264.3291268"},{"key":"1815_CR55","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ma, X., Chen, Z., Luo, Y., Yi, J., & Bailey, J. (2019). Symmetric cross entropy for robust learning with noisy labels. In: Proceedings of the IEEE\/CVF international conference on computer vision (pp 322\u2013330).","DOI":"10.1109\/ICCV.2019.00041"},{"key":"1815_CR56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3123315","author":"H Wang","year":"2021","unstructured":"Wang, H., Deng, C., Liu, T., & Tao, D. (2021). Transferable coupled network for zero-shot sketch-based image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2021.3123315","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1815_CR57","unstructured":"Xia, X., Liu, T., Han, B., Wang, N., Deng, J., Li, J., & Mao, Y. (2020). Extended t: Learning with mixed closed-set and open-set noisy labels. arXiv preprint arXiv:2012.00932"},{"key":"1815_CR58","unstructured":"Xia, X., Liu, T., Wang, N., Han, B., Gong, C., Niu, G., & Sugiyama, M. (2019) Are anchor points really indispensable in label-noise learning?. Advances in Neural Information Processing Systems 32"},{"key":"1815_CR59","unstructured":"Xiao, T., Xia, T., Yang, Y., Huang, C., Wang, X. (2015). Learning from massive noisy labeled data for image classification. In CVPR"},{"key":"1815_CR60","doi-asserted-by":"crossref","unstructured":"Xu, J., Quek, T.Q., & Chong, K.F.E. (2021) Training classifiers that are universally robust to all label noise levels. In 2021 international joint conference on neural networks (IJCNN) (pp. 1\u20138). IEEE","DOI":"10.1109\/IJCNN52387.2021.9533798"},{"key":"1815_CR61","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1109\/TPAMI.2022.3152495","volume":"45","author":"X Xu","year":"2022","unstructured":"Xu, X., Wang, Z., Deng, C., Yuan, H., & Ji, S. (2022). Towards improved and interpretable deep metric learning via attentive grouping. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 1189\u20131200.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1815_CR62","doi-asserted-by":"crossref","unstructured":"Yang, F., Wu, K., Zhang, S., Jiang, G., Liu, Y., Zheng, F., Zhang, W., Wang, C., & Zeng, L. (2022) Class-aware contrastive semi-supervised learning. arXiv preprint arXiv:2203.02261","DOI":"10.1109\/CVPR52688.2022.01402"},{"key":"1815_CR63","doi-asserted-by":"publisher","first-page":"2798","DOI":"10.1109\/TIP.2021.3055062","volume":"30","author":"Y Yang","year":"2021","unstructured":"Yang, Y., Wang, L., Xie, D., Deng, C., & Tao, D. (2021). Multi-sentence auxiliary adversarial networks for fine-grained text-to-image synthesis. IEEE Transactions on Image Processing, 30, 2798\u20132809.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1815_CR64","doi-asserted-by":"crossref","unstructured":"Yao, Y., Sun, Z., Zhang, C., Shen, F., Wu, Q., Zhang, J., Tang, Z. (2021) Jo-src: A contrastive approach for combating noisy labels. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5192\u20135201).","DOI":"10.1109\/CVPR46437.2021.00515"},{"key":"1815_CR65","first-page":"7260","volume":"33","author":"Y Yao","year":"2020","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. Advances in Neural Information Processing Systems, 33, 7260\u20137271.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"1815_CR66","doi-asserted-by":"publisher","first-page":"1909","DOI":"10.1109\/TIP.2018.2877939","volume":"28","author":"J Yao","year":"2018","unstructured":"Yao, J., Wang, J., Tsang, I. W., Zhang, Y., Sun, J., Zhang, C., & Zhang, R. (2018). Deep learning from noisy image labels with quality embedding. IEEE Transactions on Image Processing, 28(4), 1909\u20131922.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1815_CR67","doi-asserted-by":"crossref","unstructured":"Yu, Q., & Aizawa, K. (2019) Unsupervised out-of-distribution detection by maximum classifier discrepancy. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9518\u20139526).","DOI":"10.1109\/ICCV.2019.00961"},{"key":"1815_CR68","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., & Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412"},{"key":"1815_CR69","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., & Lopez-Paz, D. (2018) mixup: Beyond empirical risk minimization. In International conference on learning representations."},{"key":"1815_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, W., Wang, Y., & Qiao, Y. (2019) Metacleaner: Learning to hallucinate clean representations for noisy-labeled visual recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7373\u20137382).","DOI":"10.1109\/CVPR.2019.00755"},{"issue":"3","key":"1815_CR71","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2021). Understanding deep learning (still) requires rethinking generalization. Communications of the ACM, 64(3), 107\u2013115.","journal-title":"Communications of the ACM"},{"key":"1815_CR72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059783","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Zeng, Y., Lu, H., Zhang, L., Li, J., & Qi, J. (2021). Learning to detect salient object with multi-source weak supervision. IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2021.3059783","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01815-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01815-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01815-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,17]],"date-time":"2023-12-17T04:46:28Z","timestamp":1702788388000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01815-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,15]]},"references-count":72,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["1815"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01815-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2023,7,15]]},"assertion":[{"value":"4 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}