{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:14Z","timestamp":1777657454269,"version":"3.51.4"},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T00:00:00Z","timestamp":1714089600000},"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":["62376114"],"award-info":[{"award-number":["62376114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"crossref","award":["2021J011003 and 2021J011004"],"award-info":[{"award-number":["2021J011003 and 2021J011004"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2024,7,31]]},"abstract":"<jats:p>Existing methods based on transfer learning leverage auxiliary information to help tail generalization and improve the performance of the tail classes. However, they cannot fully exploit the relationships between auxiliary information and tail classes and bring irrelevant knowledge to the tail classes. To solve this problem, we propose a hierarchical CNN with knowledge complementation, which regards hierarchical relationships as auxiliary information and transfers relevant knowledge to tail classes. First, we integrate semantics and clustering relationships as hierarchical knowledge into the CNN to guide feature learning. Then, we design a complementary strategy to jointly exploit the two types of knowledge, where semantic knowledge acts as a prior dependence and clustering knowledge reduces the negative information caused by excessive semantic dependence (i.e., semantic gaps). In this way, the CNN facilitates the utilization of the two complementary hierarchical relationships and transfers useful knowledge to tail data to improve long-tailed classification accuracy. Experimental results on public benchmarks show that the proposed model outperforms existing methods. In particular, our model improves accuracy by 3.46% compared with the second-best method on the long-tailed tieredImageNet dataset.<\/jats:p>","DOI":"10.1145\/3653717","type":"journal-article","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T12:02:30Z","timestamp":1711108950000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Hierarchical Convolutional Neural Network with Knowledge Complementation for Long-Tailed Classification"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9339-1829","authenticated-orcid":false,"given":"Hong","family":"Zhao","sequence":"first","affiliation":[{"name":"Minnan Normal University,  Zhangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0548-254X","authenticated-orcid":false,"given":"Zhengyu","family":"Li","sequence":"additional","affiliation":[{"name":"Minnan Normal University,  Zhangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7207-1594","authenticated-orcid":false,"given":"Wenwei","family":"He","sequence":"additional","affiliation":[{"name":"Minnan Normal University,  Zhangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2295-7570","authenticated-orcid":false,"given":"Yan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Minnan Normal University,  Zhangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,26]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2458858"},{"key":"e_1_3_2_3_2","first-page":"1567","volume-title":"International Conference on Neural Information Processing Systems","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. In International Conference on Neural Information Processing Systems. 1567\u20131578."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889949"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.5555\/1622407.1622416"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.337"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_9_2","first-page":"3450","volume-title":"Conference on Computer Vision and Pattern Recognition","author":"Deng Jia","year":"2012","unstructured":"Jia Deng, Jonathan Krause, Alexander C. Berg, and Li Fei Fei. 2012. Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition. In Conference on Computer Vision and Pattern Recognition. 3450\u20133457."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3100284"},{"key":"e_1_3_2_11_2","first-page":"2835","volume-title":"International Conference on Acoustics, Speech and Signal Processing","author":"Ge Yubin","year":"2021","unstructured":"Yubin Ge, Site Li, Xuyang Li, Fangfang Fan, Wanqing Xie, Jane You, and Xiaofeng Liu. 2021. Embedding semantic hierarchy in discrete optimal transport for risk minimization. In International Conference on Acoustics, Speech and Signal Processing. 2835\u20132839."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01484"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.580"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116437"},{"key":"e_1_3_2_16_2","first-page":"1","volume-title":"International Joint Conference on Neural Networks","author":"Inoue Matheus","year":"2020","unstructured":"Matheus Inoue, Carlos Henrique Forster, and Antonio Carlos dos Santos. 2020. Semantic hierarchy-based convolutional neural networks for image classification. In International Joint Conference on Neural Networks. 1\u20138."},{"key":"e_1_3_2_17_2","first-page":"111","volume-title":"International Conference on Artificial Intelligence","author":"Japkowicz Nathalie","year":"2000","unstructured":"Nathalie Japkowicz. 2000. The class imbalance problem: Significance and strategies. In International Conference on Artificial Intelligence. 111\u2013117."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01391"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-014-0382-x"},{"key":"e_1_3_2_20_2","unstructured":"Alex Krizhevsky Vinod Nair and Geoffrey Hinton. 2009. Learning Multiple Layers of Features from Tiny Images. Master\u2019s thesis University of Toronto. 1\u201358."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.05.008"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01486"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977133"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108511"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17094"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108411"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0142716401221079"},{"key":"e_1_3_2_30_2","volume-title":"International Conference on Learning Representations","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. In International Conference on Learning Representations."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1006\/jvci.1999.0413"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108302"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.03.014"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00173"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41066-016-0032-3"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00957"},{"key":"e_1_3_2_40_2","article-title":"Coarse-to-fine: Progressive knowledge transfer based multi-task convolutional neural network for intelligent large-scale fault diagnosis","author":"Wang Yu","year":"2023","unstructured":"Yu Wang, Ruonan Liu, Di Lin, Dongyue Chen, Ping Li, Qinghua Hu, and C. L. Philip Chen. 2023. Coarse-to-fine: Progressive knowledge transfer based multi-task convolutional neural network for intelligent large-scale fault diagnosis. Transactions on Neural Networks and Learning Systems 34, 2 (2023), 761\u2013774.","journal-title":"Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_2_41_2","first-page":"7032","volume-title":"Conference on Neural Information Processing Systems","author":"Wang Yu Xiong","year":"2017","unstructured":"Yu Xiong Wang, Deva Ramanan, and Martial Hebert. 2017. Learning to model the tail. In Conference on Neural Information Processing Systems. 7032\u20137042."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0748-y"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107967"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3046566"},{"key":"e_1_3_2_46_2","first-page":"2355","volume-title":"International Conference on Acoustics, Speech and Signal Processing","author":"Zhang Renhui","year":"2022","unstructured":"Renhui Zhang, Tiancheng Lin, Rui Zhang, and Yi Xu. 2022. Solving the long-tailed problem via intra-and inter-category balance. In International Conference on Acoustics, Speech and Signal Processing. 2355\u20132359."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2960251"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2020.3005972"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.189"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108449"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007511"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3653717","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3653717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:58Z","timestamp":1750291438000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3653717"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,26]]},"references-count":51,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,7,31]]}},"alternative-id":["10.1145\/3653717"],"URL":"https:\/\/doi.org\/10.1145\/3653717","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,26]]},"assertion":[{"value":"2022-10-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}