{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:29:24Z","timestamp":1784100564489,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZB20230024,GZC20240035"],"award-info":[{"award-number":["GZB20230024,GZC20240035"]}]},{"name":"Science and Technology Support Program of Hubei Province","award":["2022BAA046"],"award-info":[{"award-number":["2022BAA046"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206102,62376103,62302184,U1936108,62025101,62088102"],"award-info":[{"award-number":["62206102,62376103,62302184,U1936108,62025101,62088102"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M750100"],"award-info":[{"award-number":["2024M750100"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680647","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"7686-7695","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6563-6603","authenticated-orcid":false,"given":"Zhenyu","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7255-2109","authenticated-orcid":false,"given":"Guangyao","family":"Chen","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2125-9041","authenticated-orcid":false,"given":"Yixiong","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8026-9349","authenticated-orcid":false,"given":"Zhimeng","family":"Huang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1846-4941","authenticated-orcid":false,"given":"Yuhua","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7791-5511","authenticated-orcid":false,"given":"Ruixuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"How to train your MAML. arXiv preprint arXiv:1810.09502","author":"Antoniou Antreas","year":"2018","unstructured":"Antreas Antoniou, Harrison Edwards, and Amos Storkey. 2018. How to train your MAML. arXiv preprint arXiv:1810.09502 (2018)."},{"key":"e_1_3_2_1_2_1","volume-title":"augment and learn: Unsupervised few-shot meta-learning via random labels and data augmentation. arXiv preprint arXiv:1902.09884","author":"Antoniou Antreas","year":"2019","unstructured":"Antreas Antoniou and Amos Storkey. 2019. Assume, augment and learn: Unsupervised few-shot meta-learning via random labels and data augmentation. arXiv preprint arXiv:1902.09884 (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00166"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8070179"},{"key":"e_1_3_2_1_5_1","volume-title":"Philip HS Torr, and Andrea Vedaldi","author":"Bertinetto Luca","year":"2018","unstructured":"Luca Bertinetto, Joao F Henriques, Philip HS Torr, and Andrea Vedaldi. 2018. Meta-learning with differentiable closed-form solvers. arXiv preprint arXiv:1805.08136 (2018)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00429"},{"key":"e_1_3_2_1_7_1","volume-title":"Unsupervised learning of visual features by contrasting cluster assignments. Advances in neural information processing systems","author":"Caron Mathilde","year":"2020","unstructured":"Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, and Armand Joulin. 2020. Unsupervised learning of visual features by contrasting cluster assignments. Advances in neural information processing systems, Vol. 33 (2020), 9912--9924."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29006"},{"key":"e_1_3_2_1_9_1","volume-title":"Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps. arXiv preprint arXiv:2210.03595","author":"Chen Kuilin","year":"2022","unstructured":"Kuilin Chen and Chi-Guhn Lee. 2022. Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps. arXiv preprint arXiv:2210.03595 (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_11_1","volume-title":"Few-shot learning with part discovery and augmentation from unlabeled images. arXiv preprint arXiv:2105.11874","author":"Chen Wentao","year":"2021","unstructured":"Wentao Chen, Chenyang Si, Wei Wang, Liang Wang, Zilei Wang, and Tieniu Tan. 2021. Few-shot learning with part discovery and augmentation from unlabeled images. arXiv preprint arXiv:2105.11874 (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"Yu-Chiang Frank Wang, and Jia-Bin Huang","author":"Chen Wei-Yu","year":"2019","unstructured":"Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang. 2019. A closer look at few-shot classification. arXiv preprint arXiv:1904.04232 (2019)."},{"key":"e_1_3_2_1_13_1","volume-title":"International Journal of Computer Vision","author":"Chen Xiaokang","year":"2023","unstructured":"Xiaokang Chen, Mingyu Ding, Xiaodi Wang, Ying Xin, Shentong Mo, Yunhao Wang, Shumin Han, Ping Luo, Gang Zeng, and Jingdong Wang. 2023. Context autoencoder for self-supervised representation learning. International Journal of Computer Vision (2023), 1--16."},{"key":"e_1_3_2_1_14_1","volume-title":"Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297","author":"Chen Xinlei","year":"2020","unstructured":"Xinlei Chen, Haoqi Fan, Ross Girshick, and Kaiming He. 2020. Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"e_1_3_2_1_16_1","volume-title":"2021 IEEE. In CVF International Conference on Computer Vision (ICCV). 9620--9629","author":"Chen X","unstructured":"X Chen, S Xie, and K He. [n.,d.]. An empirical study of training self-supervised vision transformers. In 2021 IEEE. In CVF International Conference on Computer Vision (ICCV). 9620--9629."},{"key":"e_1_3_2_1_17_1","unstructured":"Noel Codella Veronica Rotemberg Philipp Tschandl M Emre Celebi Stephen Dusza David Gutman Brian Helba Aadi Kalloo Konstantinos Liopyris Michael Marchetti et al. 2019. Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368 (2019)."},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Learning Representations.","author":"Das Debasmit","year":"2021","unstructured":"Debasmit Das, Sungrack Yun, and Fatih Porikli. 2021. ConfeSS: A framework for single source cross-domain few-shot learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","volume-title":"A baseline for few-shot image classification. arXiv preprint arXiv:1909.02729","author":"Dhillon Guneet S","year":"2019","unstructured":"Guneet S Dhillon, Pratik Chaudhari, Avinash Ravichandran, and Stefano Soatto. 2019. A baseline for few-shot image classification. arXiv preprint arXiv:1909.02729 (2019)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"e_1_3_2_1_21_1","volume-title":"Zhaohan Guo, Mohammad Gheshlaghi Azar, et al.","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, et al. 2020. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, Vol. 33 (2020), 21271--21284."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings, Part XXVII 16","author":"Guo Yunhui","year":"2020","unstructured":"Yunhui Guo, Noel C Codella, Leonid Karlinsky, James V Codella, John R Smith, Kate Saenko, Tajana Rosing, and Rogerio Feris. 2020. A broader study of cross-domain few-shot learning. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXVII 16. Springer, 124--141."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"e_1_3_2_1_26_1","volume-title":"Meta-DM: Applications of Diffusion Models on Few-Shot Learning. arXiv preprint arXiv:2305.08092","author":"Hu Wentao","year":"2023","unstructured":"Wentao Hu, Xiurong Jiang, Jiarun Liu, Yuqi Yang, and Hui Tian. 2023. Meta-DM: Applications of Diffusion Models on Few-Shot Learning. arXiv preprint arXiv:2305.08092 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification. In International Conference on Artificial Intelligence and Statistics. PMLR, 5899--5917","author":"Hu Yuqing","year":"2023","unstructured":"Yuqing Hu, St\u00e9phane Pateux, and Vincent Gripon. 2023. Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification. In International Conference on Artificial Intelligence and Statistics. PMLR, 5899--5917."},{"key":"e_1_3_2_1_28_1","volume-title":"Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning. arXiv preprint arXiv:2303.00996","author":"Jang Huiwon","year":"2023","unstructured":"Huiwon Jang, Hankook Lee, and Jinwoo Shin. 2023. Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning. arXiv preprint arXiv:2303.00996 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"URL http:\/\/www. cs. toronto. edu\/kriz\/cifar. html","author":"Krizhevsky Alex","year":"2010","unstructured":"Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton. 2010. Cifar-10 (canadian institute for advanced research). URL http:\/\/www. cs. toronto. edu\/kriz\/cifar. html, Vol. 5, 4 (2010), 1."},{"key":"e_1_3_2_1_30_1","unstructured":"Dong Bok Lee. 2021. Meta-GMVAE: Mixture of Gaussian VAEs for unsupervised meta-learning. (2021)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_24"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_43"},{"key":"e_1_3_2_1_34_1","volume-title":"BECLR: Batch Enhanced Contrastive Unsupervised Few-Shot Learning.","author":"Daktylidis Stelios Poulakakis","year":"2023","unstructured":"Stelios Poulakakis Daktylidis. 2023. BECLR: Batch Enhanced Contrastive Unsupervised Few-Shot Learning. (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"CMVAE: Causal Meta VAE for Unsupervised Meta-Learning. arXiv preprint arXiv:2302.09731","author":"Qi Guodong","year":"2023","unstructured":"Guodong Qi and Huimin Yu. 2023. CMVAE: Causal Meta VAE for Unsupervised Meta-Learning. arXiv preprint arXiv:2302.09731 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00370"},{"key":"e_1_3_2_1_37_1","volume-title":"Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676","author":"Ren Mengye","year":"2018","unstructured":"Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B Tenenbaum, Hugo Larochelle, and Richard S Zemel. 2018. Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676 (2018)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00539"},{"key":"e_1_3_2_1_40_1","volume-title":"Transductive decoupled variational inference for few-shot classification. arXiv preprint arXiv:2208.10559","author":"Singh Anuj","year":"2022","unstructured":"Anuj Singh and Hadi Jamali-Rad. 2022. Transductive decoupled variational inference for few-shot classification. arXiv preprint arXiv:2208.10559 (2022)."},{"key":"e_1_3_2_1_41_1","volume-title":"Prototypical networks for few-shot learning. Advances in neural information processing systems","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02316"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings, Part XIV 16","author":"Tian Yonglong","year":"2020","unstructured":"Yonglong Tian, Yue Wang, Dilip Krishnan, Joshua B Tenenbaum, and Phillip Isola. 2020. Rethinking few-shot image classification: a good embedding is all you need?. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XIV 16. Springer, 266--282."},{"key":"e_1_3_2_1_44_1","unstructured":"Oriol Vinyals Charles Blundell Timothy Lillicrap Daan Wierstra et al. 2016. Matching networks for one shot learning. Advances in neural information processing systems Vol. 29 (2016)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_39"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"e_1_3_2_1_47_1","volume-title":"Simpleshot: Revisiting nearest-neighbor classification for few-shot learning. arXiv preprint arXiv:1911.04623","author":"Wang Yan","year":"2019","unstructured":"Yan Wang, Wei-Lun Chao, Kilian Q Weinberger, and Laurens Van Der Maaten. 2019. Simpleshot: Revisiting nearest-neighbor classification for few-shot learning. arXiv preprint arXiv:1911.04623 (2019)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413946"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428223"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.11.073"},{"key":"e_1_3_2_1_51_1","volume-title":"Free lunch for few-shot learning: Distribution calibration. arXiv preprint arXiv:2101.06395","author":"Yang Shuo","year":"2021","unstructured":"Shuo Yang, Lu Liu, and Min Xu. 2021. Free lunch for few-shot learning: Distribution calibration. arXiv preprint arXiv:2101.06395 (2021)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179368"},{"key":"e_1_3_2_1_53_1","volume-title":"International Conference on Machine Learning. PMLR, 12310--12320","author":"Zbontar Jure","year":"2021","unstructured":"Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, and St\u00e9phane Deny. 2021. Barlow twins: Self-supervised learning via redundancy reduction. In International Conference on Machine Learning. PMLR, 12310--12320."},{"key":"e_1_3_2_1_54_1","volume-title":"Multi-level second-order few-shot learning","author":"Zhang Hongguang","year":"2022","unstructured":"Hongguang Zhang, Hongdong Li, and Piotr Koniusz. 2022. Multi-level second-order few-shot learning. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01060"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547835"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01483"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3272697"},{"key":"e_1_3_2_1_59_1","volume-title":"ibot: Image bert pre-training with online tokenizer. arXiv preprint arXiv:2111.07832","author":"Zhou Jinghao","year":"2021","unstructured":"Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, and Tao Kong. 2021. ibot: Image bert pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)."},{"key":"e_1_3_2_1_60_1","volume-title":"Image BERT Pre-training with Online Tokenizer. In International Conference on Learning Representations.","author":"Zhou Jinghao","year":"2021","unstructured":"Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, and Tao Kong. 2021. Image BERT Pre-training with Online Tokenizer. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02298"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475197"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680647","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680647"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":62,"alternative-id":["10.1145\/3664647.3680647","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680647","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}