{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:26:39Z","timestamp":1774023999533,"version":"3.50.1"},"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":[[2019,8]]},"abstract":"<jats:p>An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations. However, due to the large number of network variants, such public-available trained models are often of different architectures, each of which being tailored for a specific task or dataset. In this paper, we study a deep-model reusing task, where we are given as input pre-trained networks of heterogeneous architectures specializing in distinct tasks, as teacher models. We aim to learn a multitalented and light-weight student model that is able to grasp the integrated knowledge from all such heterogeneous-structure teachers, again without accessing any human annotation. To this end, we propose a common feature learning scheme, in which the features of all teachers are transformed into a common space and the student is enforced to imitate them all so as to amalgamate the intact knowledge. We test the proposed approach on a list of benchmarks and demonstrate that the learned student is able to achieve very promising performance, superior to those of the teachers in their specialized tasks.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/428","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:05Z","timestamp":1564299965000},"page":"3087-3093","source":"Crossref","is-referenced-by-count":33,"title":["Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning"],"prefix":"10.24963","author":[{"given":"Sihui","family":"Luo","sequence":"first","affiliation":[{"name":"Zhejiang University"}]},{"given":"Xinchao","family":"Wang","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology"}]},{"given":"Gongfan","family":"Fang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Yao","family":"Hu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Dapeng","family":"Tao","sequence":"additional","affiliation":[{"name":"Yunnan University"}]},{"given":"Mingli","family":"Song","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]}],"member":"10584","event":{"name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","theme":"Artificial Intelligence","location":"Macao, China","acronym":"IJCAI-2019","number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2019,8,10]]},"end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:49:13Z","timestamp":1564300153000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/428"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/428","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}