{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:51:59Z","timestamp":1770742319811,"version":"3.49.0"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,3,15]],"date-time":"2023-03-15T00:00:00Z","timestamp":1678838400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272461, 62276266, 62172417, and 62106268"],"award-info":[{"award-number":["62272461, 62276266, 62172417, and 62106268"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"crossref","award":["BK20180639, BK20201346"],"award-info":[{"award-number":["BK20180639, BK20201346"]}],"id":[{"id":"10.13039\/501100004608","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":[[2023,7,31]]},"abstract":"<jats:p>Meta-learning approaches have recently achieved promising performance in multi-class incremental learning. However, meta-learners still suffer from catastrophic forgetting, i.e., they tend to forget the learned knowledge from the old tasks when they focus on rapidly adapting to the new classes of the current task. To solve this problem, we propose a novel distilled meta-learning (DML) framework for multi-class incremental learning that integrates seamlessly meta-learning with knowledge distillation in each incremental stage. Specifically, during inner-loop training, knowledge distillation is incorporated into the DML to overcome catastrophic forgetting. During outer-loop training, a meta-update rule is designed for the meta-learner to learn across tasks and quickly adapt to new tasks. By virtue of the bilevel optimization, our model is encouraged to reach a balance between the retention of old knowledge and the learning of new knowledge. Experimental results on four benchmark datasets demonstrate the effectiveness of our proposal and show that our method significantly outperforms other state-of-the-art incremental learning methods.<\/jats:p>","DOI":"10.1145\/3576045","type":"journal-article","created":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T12:34:41Z","timestamp":1673958881000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Distilled Meta-learning for Multi-Class Incremental Learning"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6728-1773","authenticated-orcid":false,"given":"Hao","family":"Liu","sequence":"first","affiliation":[{"name":"China University of Mining and Technology, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9124-3048","authenticated-orcid":false,"given":"Zhaoyu","family":"Yan","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2365-6606","authenticated-orcid":false,"given":"Bing","family":"Liu","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3564-5090","authenticated-orcid":false,"given":"Jiaqi","family":"Zhao","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6207-0299","authenticated-orcid":false,"given":"Yong","family":"Zhou","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7690-8547","authenticated-orcid":false,"given":"Abdulmotaleb","family":"El Saddik","sequence":"additional","affiliation":[{"name":"University of Ottawa, Ontario, Canada"}]}],"member":"320","published-online":{"date-parts":[[2023,3,15]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"144","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV\u201918)","author":"Aljundi Rahaf","year":"2018","unstructured":"Rahaf Aljundi, Francesca Babiloni, Mohamed Elhoseiny, Marcus Rohrbach, and Tinne Tuytelaars. 2018. Memory aware synapses: Learning what (not) to forget. In Proceedings of the European Conference on Computer Vision (ECCV\u201918), Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer International Publishing, Cham, 144\u2013161."},{"key":"e_1_3_1_3_2","volume-title":"Learning a Synaptic Learning Rule","author":"Bengio Yoshua","year":"1990","unstructured":"Yoshua Bengio, Samy Bengio, and Jocelyn Cloutier. 1990. Learning a Synaptic Learning Rule. Citeseer."},{"key":"e_1_3_1_4_2","first-page":"241","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Castro F. M.","year":"2018","unstructured":"F. M. Castro, M. J. Mar\u00edn-Jim\u00e9nez, N. Guil, C. Schmid, and K. Alahari. 2018. End-to-end incremental learning. In Proceedings of the European Conference on Computer Vision. 241\u2013257."},{"key":"e_1_3_1_5_2","first-page":"532","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV\u201918)","author":"Chaudhry Arslan","year":"2018","unstructured":"Arslan Chaudhry, Puneet K. Dokania, Thalaiyasingam Ajanthan, and Philip H. S. Torr. 2018. Riemannian walk for incremental learning: Understanding forgetting and intransigence. In Proceedings of the European Conference on Computer Vision (ECCV\u201918). 532\u2013547."},{"issue":"4","key":"e_1_3_1_6_2","doi-asserted-by":"crossref","first-page":"2158","DOI":"10.1109\/TCSVT.2021.3088545","article-title":"Meta-learning-based incremental few-shot object detection","volume":"32","author":"Cheng Meng","year":"2021","unstructured":"Meng Cheng, Hanli Wang, and Yu Long. 2021. Meta-learning-based incremental few-shot object detection. IEEE Trans Circ. Syst. Vid. Technol. 32, 4 (2021), 2158\u20132169.","journal-title":"IEEE Trans Circ. Syst. Vid. Technol."},{"key":"e_1_3_1_7_2","first-page":"14166","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chi Zhixiang","year":"2022","unstructured":"Zhixiang Chi, Li Gu, Huan Liu, Yang Wang, Yuanhao Yu, and Jin Tang. 2022. MetaFSCIL: A meta-learning approach for few-shot class incremental learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 14166\u201314175."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14251"},{"key":"e_1_3_1_9_2","first-page":"6470","volume-title":"Advances in Neural Information Processing Systems","author":"Lopez-Paz M.-A. Ranzato and D.","year":"2017","unstructured":"M.-A. Ranzato and D. Lopez-Paz. 2017. Gradient episodic memory for continual learning. In Advances in Neural Information Processing Systems. 6470\u20136479."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00528"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2015.2471196"},{"key":"e_1_3_1_12_2","first-page":"4040","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201921)","author":"Douillard Arthur","year":"2021","unstructured":"Arthur Douillard, Yifu Chen, Arnaud Dapogny, and Matthieu Cord. 2021. PLOP: Learning without forgetting for continual semantic segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201921). 4040\u20134050."},{"issue":"7","key":"e_1_3_1_13_2","first-page":"38","article-title":"Distilling the knowledge in a neural network","volume":"14","author":"Hinton G.","year":"2015","unstructured":"G. Hinton, O. Vinyals, and J. Dean. 2015. Distilling the knowledge in a neural network. Comput. Sci. 14, 7 (2015), 38\u201339.","journal-title":"Comput. Sci."},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"e_1_3_1_15_2","first-page":"1","volume-title":"Advances in Neural Information Processing Systems","author":"Javed Khurram","year":"2019","unstructured":"Khurram Javed and Martha White. 2019. Meta-learning representations for continual learning. In Advances in Neural Information Processing Systems, Vol. 32. 1\u201315."},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_1_17_2","first-page":"1","article-title":"Incremental object detection via meta-learning","author":"Kj Joseph","year":"2021","unstructured":"Joseph Kj, Jathushan Rajasegaran, Salman Khan, Fahad Shahbaz Khan, and Vineeth N. Balasubramanian. 2021. Incremental object detection via meta-learning. IEEE Trans. Pattern Anal. Mach. Intell. (2021), 1\u201311.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_1_18_2","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"Krizhevsky A.","year":"2009","unstructured":"A. Krizhevsky and G. Hinton. 2009. Learning multiple layers of features from tiny images. Computer Science Department, University of Toronto, Technical Report 1 (012009).","journal-title":"Computer Science Department, University of Toronto, Technical Report"},{"issue":"288","key":"e_1_3_1_19_2","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/S0304-3975(01)00404-2","article-title":"On the power of incremental learning","volume":"2","author":"Lange S.","year":"2002","unstructured":"S. Lange and G. Grieser. 2002. On the power of incremental learning. Theor. Comput. Sci. 2, 288 (2002), 277\u2013307.","journal-title":"Theor. Comput. Sci."},{"key":"e_1_3_1_20_2","unstructured":"Y. Lecun and C. Cortes. 2010. The mnist Database of Handwritten Digits. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"e_1_3_1_22_2","article-title":"On the variance of the adaptive learning rate and beyond","author":"Liu Liyuan","year":"2019","unstructured":"Liyuan Liu, Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao, and Jiawei Han. 2019. On the variance of the adaptive learning rate and beyond. arXiv:1908.03265. Retrieved from https:\/\/arxiv.org\/abs\/1908.03265.","journal-title":"arXiv:1908.03265"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545895"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490598"},{"key":"e_1_3_1_25_2","first-page":"2544","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu Yaoyao","year":"2021","unstructured":"Yaoyao Liu, Bernt Schiele, and Qianru Sun. 2021. Adaptive aggregation networks for class-incremental learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2544\u20132553."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01226"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00504"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2008326"},{"key":"e_1_3_1_30_2","first-page":"1","volume-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011","author":"Netzer Yuval","year":"2011","unstructured":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng. 2011. Reading digits in natural images with unsupervised feature learning. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011. 1\u20139."},{"key":"e_1_3_1_31_2","article-title":"On first-order meta-learning algorithms","author":"Nichol Alex","year":"2018","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.","journal-title":"arXiv:1803.02999"},{"key":"e_1_3_1_32_2","article-title":"Reptile: A scalable metalearning algorithm","author":"Nichol Alex","year":"2018","unstructured":"Alex Nichol and John Schulman. 2018. Reptile: A scalable metalearning algorithm. arXiv:1803.02999. Retrieved from https:\/\/arxiv.org\/abs\/1803.02999.","journal-title":"arXiv:1803.02999"},{"key":"e_1_3_1_33_2","first-page":"1","article-title":"Random path selection for incremental learning","author":"Rajasegaran Jathushan","year":"2019","unstructured":"Jathushan Rajasegaran, Munawar Hayat, Salman Khan, Fahad Shahbaz Khan, and Ling Shao. 2019. Random path selection for incremental learning. Advances in Neural Information Processing Systems (2019), 1\u201311.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01360"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2001.989589"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.131"},{"key":"e_1_3_1_39_2","first-page":"2290","volume-title":"Advances in Neural Information Processing Systems","author":"Shin Hanul","year":"2017","unstructured":"Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. 2017. Continual learning with deep generative replay. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. 2290\u20132999."},{"key":"e_1_3_1_40_2","first-page":"987","volume-title":"Proceedings of the 15th ACM International Conference on Web Search and Data Mining","author":"Tan Zhen","year":"2022","unstructured":"Zhen Tan, Kaize Ding, Ruocheng Guo, and Huan Liu. 2022. Graph few-shot class-incremental learning. In Proceedings of the 15th ACM International Conference on Web Search and Data Mining. 987\u2013996."},{"key":"e_1_3_1_41_2","first-page":"3729","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang Kai","year":"2022","unstructured":"Kai Wang, Xialei Liu, Andrew D. Bagdanov, Luis Herranz, Shangling Jui, and Joost van de Weijer. 2022. Incremental meta-learning via episodic replay distillation for few-shot image recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3729\u20133739."},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472393"},{"key":"e_1_3_1_44_2","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume":"70","author":"Zenke F.","year":"2017","unstructured":"F. Zenke, B. Poole, and S. Ganguli. 2017. Continual learning through synaptic intelligence. Int. Conf. Mach. Learn. 70 (2017), 3987\u20133995.","journal-title":"Int. Conf. Mach. Learn."},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/wacv45572.2020.9093365"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475306"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3576045","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3576045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:39Z","timestamp":1750182579000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3576045"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,15]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,7,31]]}},"alternative-id":["10.1145\/3576045"],"URL":"https:\/\/doi.org\/10.1145\/3576045","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,15]]},"assertion":[{"value":"2022-06-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-07","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}