{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:41:54Z","timestamp":1772905314700,"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":[[2018,7]]},"abstract":"<jats:p>We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks and merges them into a unified model by sharing the representative codes of weights.\n\nThe shared weights are further re-trained to fine-tune the performance of the merged model. The proposed method effectively produces a compact model that may run original tasks simultaneously on resource-limited devices. As it preserves the general architectures and leverages the co-used weights of well-trained networks, a substantial training overhead can be reduced to shorten the system development time. Experimental results demonstrate a satisfactory performance and validate the effectiveness of the method.<\/jats:p>","DOI":"10.24963\/ijcai.2018\/283","type":"proceedings-article","created":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:49:10Z","timestamp":1530755350000},"page":"2049-2056","source":"Crossref","is-referenced-by-count":23,"title":["Unifying and Merging Well-trained Deep Neural Networks for Inference Stage"],"prefix":"10.24963","author":[{"given":"Yi-Min","family":"Chou","sequence":"first","affiliation":[{"name":"Institute of Information Science, Academia Sinica"},{"name":"MOST Joint Research Center for AI Technology and All Vista Healthcare"}]},{"given":"Yi-Ming","family":"Chan","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica"},{"name":"MOST Joint Research Center for AI Technology and All Vista Healthcare"}]},{"given":"Jia-Hong","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica"},{"name":"MOST Joint Research Center for AI Technology and All Vista Healthcare"}]},{"given":"Chih-Yi","family":"Chiu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Chiayi University"}]},{"given":"Chu-Song","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica"},{"name":"MOST Joint Research Center for AI Technology and All Vista Healthcare"}]}],"member":"10584","event":{"name":"Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}","theme":"Artificial Intelligence","location":"Stockholm, Sweden","acronym":"IJCAI-2018","number":"27","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2018,7,13]]},"end":{"date-parts":[[2018,7,19]]}},"container-title":["Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:51:28Z","timestamp":1530755488000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2018\/283"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2018\/283","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}