{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T19:37:44Z","timestamp":1773517064635,"version":"3.50.1"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62506123, and 62476281"],"award-info":[{"award-number":["62506123, and 62476281"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>\n                    Metric-based methods, such as ProtoNet, excel in few-shot image classification by encouraging similarity to class prototypes. However, prototypes built from limited samples often capture only partial class information, limiting performance. Recent distribution estimation-based methods attempt to enhance performance by leveraging similar base class distributions. Yet, these approaches struggle when the distributions of base and novel classes differ significantly. Empirical analysis reveals that conceptually related categories share a local-global semantic invariance even under large distribution gaps. Based on this insight, a Self-Regressive Prototype Refinement (SRPR) is proposed to address the issue of incomplete prototype representations in few-shot learning. SRPR estimates an optimization direction for local embeddings, progressively refining them toward more global representations by exploiting local-global semantic invariance in base class data. The conservative use of coarse-grained local-global semantic structures, rather than relying on similar distributions, enhances SRPR\u2019s applicability. With minimal computational overhead per refinement step, SRPR significantly improves classification performance and achieves state-of-the-art results across multiple few-shot benchmarks, particularly in the challenging 1-shot setting. Code is available at:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/giraffe2021\/SRPR\">https:\/\/github.com\/giraffe2021\/SRPR<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3794850","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T11:51:07Z","timestamp":1770378667000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-Regressive Prototype Refinement: Stepping from Local to Global Prototypes in Few-Shot Image Classification"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6475-8169","authenticated-orcid":false,"given":"Zhenyu","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1012-5301","authenticated-orcid":false,"given":"Qing","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7926-3310","authenticated-orcid":false,"given":"Tianrui","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9329-1411","authenticated-orcid":false,"given":"Lei","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9066-1475","authenticated-orcid":false,"given":"Xinwang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5040-3774","authenticated-orcid":false,"given":"En","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,7]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_2"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00881"},{"key":"e_1_3_1_4_2","first-page":"3981","volume-title":"Advances in Neural Information Processing Systems","author":"Andrychowicz Marcin","year":"2016","unstructured":"Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, and Nando De Freitas. 2016. Learning to learn by gradient descent by gradient descent. In Advances in Neural Information Processing Systems, 3981\u20133989."},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3143692"},{"key":"e_1_3_1_6_2","first-page":"3336","article-title":"A two-stage approach to few-shot learning for image recognition","volume":"29","author":"Das Debasmit","year":"2019","unstructured":"Debasmit Das and C. S. George Lee. 2019. A two-stage approach to few-shot learning for image recognition. IEEE Transactions on Image Processing 29 (2019), 3336\u20133350.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2008"},{"key":"e_1_3_1_8_2","unstructured":"Yingjun Du Xiantong Zhen Ling Shao and Cees G. M. Snoek. 2021. Hierarchical variational memory for few-shot learning across domains. arXiv:2112.08181. Retrieved from https:\/\/arxiv.org\/abs\/2112.08181"},{"key":"e_1_3_1_9_2","first-page":"1126","volume-title":"International Conference on Machine Learning","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning. PMLR, 1126\u20131135."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511917"},{"key":"e_1_3_1_11_2","first-page":"4005","article-title":"Cross attention network for few-shot classification","volume":"32","author":"Hou Ruibing","year":"2019","unstructured":"Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, and Xilin Chen. 2019. Cross attention network for few-shot classification. Advances in Neural Information Processing Systems 32 (2019), 4005\u20134016.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2957187"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3011526"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.17021"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00743"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3582689"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3273291"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17047"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_43"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/123"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01401"},{"key":"e_1_3_1_22_2","first-page":"3664","volume-title":"International Conference on Machine Learning","author":"Munkhdalai Tsendsuren","year":"2018","unstructured":"Tsendsuren Munkhdalai, Xingdi Yuan, Soroush Mehri, and Adam Trischler. 2018. Rapid adaptation with conditionally shifted neurons. In International Conference on Machine Learning. PMLR, 3664\u20133673."},{"key":"e_1_3_1_23_2","unstructured":"Alex Nichol Joshua Achiam and John Schulman. 2018. On first-order meta-learning algorithms. arXiv:1803.02999. Retrieved from https:\/\/arxiv.org\/abs\/1803.02999"},{"key":"e_1_3_1_24_2","unstructured":"Boris N. Oreshkin Pau Rodriguez and Alexandre Lacoste. 2018. Tadam: Task dependent adaptive metric for improved few-shot learning. arXiv:1805.10123. Retrieved from https:\/\/arxiv.org\/abs\/1805.10123"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00755"},{"key":"e_1_3_1_26_2","first-page":"8748","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748\u20138763."},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2861573"},{"key":"e_1_3_1_28_2","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:1803.00676. Retrieved from https:\/\/arxiv.org\/abs\/1803.00676"},{"key":"e_1_3_1_29_2","unstructured":"Andrei A. Rusu Dushyant Rao Jakub Sygnowski Oriol Vinyals Razvan Pascanu Simon Osindero and Raia Hadsell. 2018. Meta-learning with latent embedding optimization. arXiv:1807.05960. Retrieved from https:\/\/arxiv.org\/abs\/1807.05960"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3608478"},{"key":"e_1_3_1_31_2","first-page":"4077","article-title":"Prototypical networks for few-shot learning","volume":"30","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 30 (2017), 4077\u20134087.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"e_1_3_1_34_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Triantafillou Eleni","year":"2020","unstructured":"Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Umut Evci, Kelvin Xu, Ross Goroshin, Chris Gelada, Kevin J. Swersky, Pierre-Antoine Manzagol, and Hugo Larochelle. 2020. Meta-dataset: A dataset of datasets for learning to learn from few examples. In Proceedings of the International Conference on Learning Representations (ICLR), 1\u201319. OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=MMwaQEVsAg"},{"key":"e_1_3_1_35_2","first-page":"3630","article-title":"Matching networks for one shot learning","volume":"29","author":"Vinyals Oriol","year":"2016","unstructured":"Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, and Daan Wierstra. 2016. Matching networks for one shot learning. Advances in Neural Information Processing Systems 29 (2016), 3630\u20133638.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083650"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00672"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00792"},{"key":"e_1_3_1_39_2","unstructured":"Jiangtao Xie Fei Long Jiaming Lv Qilong Wang and Peihua Li. 2022. Joint distribution matters: Deep Brownian distance covariance for few-shot classification. arXiv:2204.04567. Retrieved from https:\/\/arxiv.org\/abs\/2204.04567"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00514"},{"key":"e_1_3_1_41_2","unstructured":"Shuo Yang Lu Liu and Min Xu. 2021. Free lunch for few-shot learning: Distribution calibration. arXiv:2101.06395. Retrieved from https:\/\/arxiv.org\/abs\/2101.06395"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29608"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109235"},{"key":"e_1_3_1_46_2","first-page":"9122","article-title":"Learning to learn variational semantic memory","volume":"33","author":"Zhen Xiantong","year":"2020","unstructured":"Xiantong Zhen, Yingjun Du, Huan Xiong, Qiang Qiu, Cees Snoek, and Ling Shao. 2020. Learning to learn variational semantic memory. Advances in Neural Information Processing Systems 33 (2020), 9122\u20139134.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3694686"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3310329"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3243903"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3794850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T13:24:39Z","timestamp":1773494679000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3794850"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,7]]},"references-count":48,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3794850"],"URL":"https:\/\/doi.org\/10.1145\/3794850","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,7]]},"assertion":[{"value":"2025-04-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}