{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T15:19:58Z","timestamp":1776525598238,"version":"3.51.2"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:p>Although deep learning has demonstrated its outstanding performance on image classification, most well-known deep networks make efforts to optimize both their structures and their node weights for recognizing fewer (e.g., no more than 1000) object classes. Therefore, it is attractive to extend or mixture such well-known deep networks to support large-scale image classification. According to our best knowledge, how to adaptively and effectively fuse multiple CNNs for large-scale image classification is still under-explored. On this basis, a deep mixture algorithm is developed to support large-scale image classification in this paper. First, a soft spectral clustering method is developed to construct a two-layer ontology (group layer and category layer) by assigning large numbers of image categories into a set of groups according to their inter-category semantic correlations, where the semantically-related image categories under the neighbouring group nodes may share similar learning complexities. Then, such two-layer ontology is further used to generate the task groups, in which each task group contains partial image categories with similar learning complexities and one particular base deep network is learned. Finally, a gate network is learned to combine all base deep networks with fewer diverse outputs to generate a mixture network with larger outputs. Our experimental results on ImageNet10K have demonstrated that our proposed deep mixture algorithm can achieve very competitive results (top 1 accuracy: 32.13%) on large-scale image classification tasks.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/100","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T07:00:49Z","timestamp":1628665249000},"page":"722-728","source":"Crossref","is-referenced-by-count":3,"title":["DeepME: Deep Mixture Experts for Large-scale Image Classification"],"prefix":"10.24963","author":[{"given":"Ming","family":"He","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China"},{"name":"University of Science and Technology of China, Hefei, Anhui 230000, China"},{"name":"Didi Chuxing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyi","family":"Lv","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui 230000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weidong","family":"He","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui 230000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianping","family":"Fan","sequence":"additional","affiliation":[{"name":"AI Lab at Lenovo Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guihua","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","theme":"Artificial Intelligence","location":"Montreal, Canada","acronym":"IJCAI-2021","number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2021,8,19]]},"end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T07:01:22Z","timestamp":1628665282000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2021\/100"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2021\/100","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}