{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T04:23:56Z","timestamp":1777350236002,"version":"3.51.4"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"5s","license":[{"start":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T00:00:00Z","timestamp":1686096000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"European Commission under European Horizon 2020 Programme","award":["951911 - AI4Media"],"award-info":[{"award-number":["951911 - AI4Media"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2023,10,31]]},"abstract":"<jats:p><jats:bold>Deep neural networks (DNNs)<\/jats:bold>for social image classification are prone to performance reduction and overfitting when trained on datasets plagued by noisy or imbalanced labels. Weight loss methods tend to ignore the influence of noisy or frequent category examples during the training, resulting in a reduction of final accuracy and, in the presence of extreme noise, even a failure of the learning process. A new advisor network is introduced to address both imbalance and noise problems, and is able to pilot learning of a main network by adjusting the visual features and the gradient with a meta-learning strategy. In a curriculum learning fashion, the impact of redundant data is reduced while recognizable noisy label images are downplayed or redirected.<jats:bold>Meta Feature Re-Weighting (MFRW)<\/jats:bold>and<jats:bold>Meta Equalization Softmax (MES)<\/jats:bold>methods are introduced to let the main network focus only on the information in an image deemed relevant by the advisor network and to adjust the training gradient to reduce the adverse effects of frequent or noisy categories. The proposed method is first tested on synthetic versions of CIFAR10 and CIFAR100, and then on the more realistic ImageNet-LT, Places-LT, and Clothing1M datasets, reporting state-of-the-art results.<\/jats:p>","DOI":"10.1145\/3584360","type":"journal-article","created":{"date-parts":[[2023,2,18]],"date-time":"2023-02-18T06:19:22Z","timestamp":1676701162000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Meta-learning Advisor Networks for Long-tail and Noisy Labels in Social Image Classification"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9838-6076","authenticated-orcid":false,"given":"Simone","family":"Ricci","sequence":"first","affiliation":[{"name":"University of Florence, IT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1025-4541","authenticated-orcid":false,"given":"Tiberio","family":"Uricchio","sequence":"additional","affiliation":[{"name":"University of Florence, IT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1052-8322","authenticated-orcid":false,"given":"Alberto","family":"Del Bimbo","sequence":"additional","affiliation":[{"name":"University of Florence, IT"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,7]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106771"},{"key":"e_1_3_1_3_2","first-page":"312","volume-title":"International Conference on Machine Learning","author":"Arazo Eric","year":"2019","unstructured":"Eric Arazo, Diego Ortego, Paul Albert, Noel O\u2019Connor, and Kevin McGuinness. 2019. Unsupervised label noise modeling and loss correction. In International Conference on Machine Learning. PMLR, 312\u2013321."},{"key":"e_1_3_1_4_2","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","author":"Cao Kaidi","year":"2019","unstructured":"Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Arechiga, and Tengyu Ma. 2019. Learning imbalanced datasets with label-distribution-aware margin loss. arXiv preprint arXiv:1906.07413 (2019).","journal-title":"arXiv preprint arXiv:1906.07413"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_3_1_6_2","first-page":"14097","article-title":"Generalized DataWeighting via class-level gradient manipulation","volume":"34","author":"Chen Can","year":"2021","unstructured":"Can Chen, Shuhao Zheng, Xi Chen, Erqun Dong, Xue Steve Liu, Hao Liu, and Dejing Dou. 2021. Generalized DataWeighting via class-level gradient manipulation. Advances in Neural Information Processing Systems 34 (2021), 14097\u201314109.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.529"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_41"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_1_12_2","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries Terrance","year":"2017","unstructured":"Terrance DeVries and Graham W. Taylor. 2017. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017).","journal-title":"arXiv preprint arXiv:1708.04552"},{"key":"e_1_3_1_13_2","volume-title":"ICML-KDD 2003 Workshop: Learning from Imbalanced Datasets","author":"Drummond Chris","year":"2003","unstructured":"Chris Drummond. 2003. Class imbalance and cost sensitivity: Why undersampling beats oversampling. In ICML-KDD 2003 Workshop: Learning from Imbalanced Datasets, Vol. 3."},{"key":"e_1_3_1_14_2","unstructured":"Jacob Goldberger and Ehud Ben-Reuven. 2016. Training deep neural-networks using a noise adaptation layer. (2016)."},{"key":"e_1_3_1_15_2","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","author":"Han Bo","year":"2018","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. arXiv preprint arXiv:1804.06872 (2018).","journal-title":"arXiv preprint arXiv:1804.06872"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_91"},{"key":"e_1_3_1_17_2","first-page":"10456","article-title":"Using trusted data to train deep networks on labels corrupted by severe noise","volume":"31","author":"Hendrycks Dan","year":"2018","unstructured":"Dan Hendrycks, Mantas Mazeika, Duncan Wilson, and Kevin Gimpel. 2018. Using trusted data to train deep networks on labels corrupted by severe noise. Advances in Neural Information Processing Systems 31 (2018), 10456\u201310465.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.580"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00763"},{"key":"e_1_3_1_20_2","first-page":"4804","volume-title":"International Conference on Machine Learning","author":"Jiang Lu","year":"2020","unstructured":"Lu Jiang, Di Huang, Mason Liu, and Weilong Yang. 2020. Beyond synthetic noise: Deep learning on controlled noisy labels. In International Conference on Machine Learning. PMLR, 4804\u20134815."},{"key":"e_1_3_1_21_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_1_22_2","article-title":"Decoupling representation and classifier for long-tailed recognition","author":"Kang Bingyi","year":"2019","unstructured":"Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, and Yannis Kalantidis. 2019. Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217 (2019).","journal-title":"arXiv preprint arXiv:1910.09217"},{"key":"e_1_3_1_23_2","article-title":"Learning from long-tailed data with noisy labels","author":"Karthik Shyamgopal","year":"2021","unstructured":"Shyamgopal Karthik, J\u00e9rome Revaud, and Boris Chidlovskii. 2021. Learning from long-tailed data with noisy labels. arXiv preprint arXiv:2108.11096 (2021).","journal-title":"arXiv preprint arXiv:2108.11096"},{"issue":"8","key":"e_1_3_1_24_2","doi-asserted-by":"crossref","first-page":"3573","DOI":"10.1109\/TNNLS.2017.2732482","article-title":"Cost-sensitive learning of deep feature representations from imbalanced data","volume":"29","author":"Khan Salman H.","year":"2017","unstructured":"Salman H. Khan, Munawar Hayat, Mohammed Bennamoun, Ferdous A. Sohel, and Roberto Togneri. 2017. Cost-sensitive learning of deep feature representations from imbalanced data. IEEE Transactions on Neural Networks and Learning Systems 29, 8 (2017), 3573\u20133587.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_1_25_2","article-title":"Adam: A method for stochastic optimization","author":"Kingma Diederik P.","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27671-7_5"},{"key":"e_1_3_1_27_2","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume":"23","author":"Kumar M.","year":"2010","unstructured":"M. Kumar, Benjamin Packer, and Daphne Koller. 2010. Self-paced learning for latent variable models. Advances in Neural Information Processing Systems 23 (2010), 1189\u20131197.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_28_2","volume-title":"International Conference on Learning Representations","author":"Li Junnan","year":"2020","unstructured":"Junnan Li, Richard Socher, and Steven C. H. Hoi. 2020. DivideMix: Learning with noisy labels as semi-supervised learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HJgExaVtwr."},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00519"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357912"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2906152"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_1_33_2","first-page":"20331","article-title":"Early-learning regularization prevents memorization of noisy labels","volume":"33","author":"Liu Sheng","year":"2020","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.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"e_1_3_1_35_2","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. SGDR: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016).","journal-title":"arXiv preprint arXiv:1608.03983"},{"key":"e_1_3_1_36_2","first-page":"3355","volume-title":"International Conference on Machine Learning","author":"Ma Xingjun","year":"2018","unstructured":"Xingjun Ma, Yisen Wang, Michael E. Houle, Shuo Zhou, Sarah Erfani, Shutao Xia, Sudanthi Wijewickrema, and James Bailey. 2018. Dimensionality-driven learning with noisy labels. In International Conference on Machine Learning. PMLR, 3355\u20133364."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2018.00042"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-010-9156-z"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00793"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS.2006.65"},{"key":"e_1_3_1_43_2","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"Reed Scott","year":"2014","unstructured":"Scott Reed, Honglak Lee, Dragomir Anguelov, Christian Szegedy, Dumitru Erhan, and Andrew Rabinovich. 2014. Training deep neural networks on noisy labels with bootstrapping. arXiv preprint arXiv:1412.6596 (2014).","journal-title":"arXiv preprint arXiv:1412.6596"},{"key":"e_1_3_1_44_2","article-title":"Balanced meta-softmax for long-tailed visual recognition","author":"Ren Jiawei","year":"2020","unstructured":"Jiawei Ren, Cunjun Yu, Shunan Sheng, Xiao Ma, Haiyu Zhao, Shuai Yi, and Hongsheng Li. 2020. Balanced meta-softmax for long-tailed visual recognition. arXiv preprint arXiv:2007.10740 (2020).","journal-title":"arXiv preprint arXiv:2007.10740"},{"key":"e_1_3_1_45_2","first-page":"4334","volume-title":"International Conference on Machine Learning","author":"Ren Mengye","year":"2018","unstructured":"Mengye Ren, Wenyuan Zeng, Bin Yang, and Raquel Urtasun. 2018. Learning to reweight examples for robust deep learning. In International Conference on Machine Learning. PMLR, 4334\u20134343."},{"key":"e_1_3_1_46_2","first-page":"1919","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Shu Jun","year":"2019","unstructured":"Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, and Deyu Meng. 2019. Meta-weight-net: Learning an explicit mapping for sample weighting. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. 1919\u20131930."},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"issue":"11","key":"e_1_3_1_49_2","article-title":"Visualizing data using t-SNE.","volume":"9","author":"Maaten Laurens Van der","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 11 (2008).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295446"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00458"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"e_1_3_1_53_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_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00021"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00718"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00585"},{"key":"e_1_3_1_57_2","volume-title":"International Conference on Learning Representations","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, and David Lopez-Paz. 2018. Mixup: Beyond empirical risk minimization. In International Conference on Learning Representations."},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00440"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3584360","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3584360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:54Z","timestamp":1750182534000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3584360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,7]]},"references-count":59,"journal-issue":{"issue":"5s","published-print":{"date-parts":[[2023,10,31]]}},"alternative-id":["10.1145\/3584360"],"URL":"https:\/\/doi.org\/10.1145\/3584360","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,7]]},"assertion":[{"value":"2022-01-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-06","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}