{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:56:40Z","timestamp":1781539000125,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":37,"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"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62171391"],"award-info":[{"award-number":["62171391"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810804","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"535-543","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Pseudo-Labeling and Representation Balance in Realistic Long-Tailed Semi-Supervised Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8495-1055","authenticated-orcid":false,"given":"Zhengyu","family":"Ma","sequence":"first","affiliation":[{"name":"School of Aerospace Engineering, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3583-6943","authenticated-orcid":false,"given":"Qifeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Aerospace Engineering, Xiamen University, Xiamen, 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\/IJCNN48605.2020.9207304"},{"key":"e_1_3_3_1_3_2","unstructured":"David Berthelot Nicholas Carlini Ekin\u00a0D Cubuk Alex Kurakin Kihyuk Sohn Han Zhang and Colin Raffel. 2019. Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1911.09785 (2019)."},{"key":"e_1_3_3_1_4_2","unstructured":"David Berthelot Nicholas Carlini Ian Goodfellow Nicolas Papernot Avital Oliver and Colin\u00a0A Raffel. 2019. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_5_2","first-page":"365","volume-title":"CEUR Workshop Proceedings","volume":"2563","author":"Bhatia Snehal","year":"2019","unstructured":"Snehal Bhatia and Rozenn Dahyot. 2019. Using WGAN for improving imbalanced classification performance. In CEUR Workshop Proceedings , Vol.\u00a02563. CEUR, 365\u2013375."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Mateusz Buda Atsuto Maki and Maciej\u00a0A Mazurowski. 2018. A systematic study of the class imbalance problem in convolutional neural networks. Neural networks 106 (2018) 249\u2013259.","DOI":"10.1016\/j.neunet.2018.07.011"},{"key":"e_1_3_3_1_7_2","unstructured":"Kaidi Cao Colin Wei Adrien Gaidon Nikos Arechiga and Tengyu Ma. 2019. Learning imbalanced datasets with label-distribution-aware margin loss. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Nitesh\u00a0V Chawla Kevin\u00a0W Bowyer Lawrence\u00a0O Hall and W\u00a0Philip Kegelmeyer. 2002. SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research 16 (2002) 321\u2013357.","DOI":"10.1613\/jair.953"},{"key":"e_1_3_3_1_9_2","first-page":"215","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Coates Adam","year":"2011","unstructured":"Adam Coates, Andrew Ng, and Honglak Lee. 2011. An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 215\u2013223."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00075"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Damien Dablain Bartosz Krawczyk and Nitesh\u00a0V Chawla. 2022. DeepSMOTE: Fusing deep learning and SMOTE for imbalanced data. IEEE transactions on neural networks and learning systems 34 9 (2022) 6390\u20136404.","DOI":"10.1109\/TNNLS.2021.3136503"},{"key":"e_1_3_3_1_12_2","unstructured":"Chaoqun Du Yizeng Han and Gao Huang. 2024. Simpro: A simple probabilistic framework towards realistic long-tailed semi-supervised learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.13505 (2024)."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Chaoqun Du Yulin Wang Shiji Song and Gao Huang. 2024. Probabilistic contrastive learning for long-tailed visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 9 (2024) 5890\u20135904.","DOI":"10.1109\/TPAMI.2024.3369102"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01417"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Yue Geng and Xinyu Luo. 2019. Cost-sensitive convolutional neural networks for imbalanced time series classification. Intelligent Data Analysis 23 2 (2019) 357\u2013370.","DOI":"10.3233\/IDA-183831"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Xiaoyu Guo Xiang Wei Shunli Zhang Wei Lu and Weiwei Xing. 2024. DCRP: Class-Aware Feature Diffusion Constraint and Reliable Pseudo-Labeling for Imbalanced Semi-Supervised Learning. IEEE Transactions on Multimedia 26 (2024) 7146\u20137159.","DOI":"10.1109\/TMM.2024.3360704"},{"key":"e_1_3_3_1_17_2","unstructured":"Yaxin Hou Bo Han Yuheng Jia Hui Liu and Junhui Hou. 2025. Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.03993 (2025)."},{"key":"e_1_3_3_1_18_2","unstructured":"Yaxin Hou and Yuheng Jia. 2025. A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.16341 (2025)."},{"key":"e_1_3_3_1_19_2","unstructured":"Zhiyuan Huang Jiahao Chen Yurou Liu and Bing Su. 2025. LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.09926 (2025)."},{"key":"e_1_3_3_1_20_2","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:https:\/\/arXiv.org\/abs\/1910.09217 (2019)."},{"key":"e_1_3_3_1_21_2","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_3_1_22_2","first-page":"896","volume-title":"Workshop on challenges in representation learning, ICML","author":"Lee Dong-Hyun","year":"2013","unstructured":"Dong-Hyun Lee et\u00a0al. 2013. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML , Vol.\u00a03. Atlanta, 896."},{"key":"e_1_3_3_1_23_2","unstructured":"Hyuck Lee Seungjae Shin and Heeyoung Kim. 2021. Abc: Auxiliary balanced classifier for class-imbalanced semi-supervised learning. Advances in Neural Information Processing Systems 34 (2021) 7082\u20137094."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00682"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Lu Liu and Robby\u00a0T Tan. 2021. Certainty driven consistency loss on multi-teacher networks for semi-supervised learning. Pattern Recognition 120 (2021) 108140.","DOI":"10.1016\/j.patcog.2021.108140"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29334"},{"key":"e_1_3_3_1_27_2","unstructured":"Aditya\u00a0Krishna Menon Sadeep Jayasumana Ankit\u00a0Singh Rawat Himanshu Jain Andreas Veit and Sanjiv Kumar. 2020. Long-tail learning via logit adjustment. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2007.07314 (2020)."},{"key":"e_1_3_3_1_28_2","first-page":"76","volume-title":"Third international workshop on learning with imbalanced domains: Theory and applications","author":"Nazari Ehsan","year":"2021","unstructured":"Ehsan Nazari and Paula Branco. 2021. On oversampling via generative adversarial networks under different data difficulty factors. In Third international workshop on learning with imbalanced domains: Theory and applications. PMLR, 76\u201389."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00956"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Wujian Peng Zejia Weng Hengduo Li Zuxuan Wu and Yu-Gang Jiang. 2025. Bmb: Balanced memory bank for long-tailed semi-supervised learning. IEEE Transactions on Multimedia (2025).","DOI":"10.1109\/TMM.2025.3535115"},{"key":"e_1_3_3_1_31_2","unstructured":"Kihyuk Sohn David Berthelot Nicholas Carlini Zizhao Zhang Han Zhang Colin\u00a0A Raffel Ekin\u00a0Dogus Cubuk Alexey Kurakin and Chun-Liang Li. 2020. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems 33 (2020) 596\u2013608."},{"key":"e_1_3_3_1_32_2","unstructured":"Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_33_2","unstructured":"Yidong Wang Hao Chen Qiang Heng Wenxin Hou Yue Fan Zhen Wu Jindong Wang Marios Savvides Takahiro Shinozaki Bhiksha Raj et\u00a0al. 2022. Freematch: Self-adaptive thresholding for semi-supervised learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.07246 (2022)."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01071"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00338"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Xiang Wei Xiaotao Wei Xiangyuan Kong Siyang Lu Weiwei Xing and Wei Lu. 2021. FMixCutMatch for semi-supervised deep learning. Neural Networks 133 (2021) 166\u2013176.","DOI":"10.1016\/j.neunet.2020.10.018"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Xiaotao Wei Xiang Wei Weiwei Xing Siyang Lu and Wei Lu. 2020. An incremental self-labeling strategy for semi-supervised deep learning based on generative adversarial networks. IEEE Access 8 (2020) 8913\u20138921.","DOI":"10.1109\/ACCESS.2020.2964315"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1605.07146 (2016).","DOI":"10.5244\/C.30.87"}],"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":"2026-06-15T15:31:20Z","timestamp":1781537480000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810804"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":37,"alternative-id":["10.1145\/3805622.3810804","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810804","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"}}]}}