{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T15:53:47Z","timestamp":1774626827693,"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>Despite deep neural networks have\ndemonstrated strong power in face photo-sketch synthesis task, their\nperformance, however, are still limited by the lack of training data\n(photo-sketch pairs). Knowledge Transfer (KT), which aims at training a smaller\nand fast student network with the information learned from a larger and\naccurate teacher network, has attracted much attention recently due to its\nsuperior performance in the acceleration and compression of deep neural\nnetworks. This work has brought us great inspiration that we can train a\nrelatively small student network on very few training data by transferring\nknowledge from a larger teacher model trained on enough training data for other\ntasks. Therefore, we propose a novel knowledge transfer framework to synthesize\nface photos from face sketches or synthesize face sketches from face photos.\nParticularly, we utilize two teacher networks trained on large amount of data\nin related task to learn the knowledge of face photos and face sketches\nseparately and transfer them to two student networks simultaneously. In\naddition, the two student networks, one for photo ? sketch task and the other for sketch ? photo task, can transfer their knowledge mutually. With the\nproposed method, we can train our model which has superior performance using a\nsmall set of photo-sketch pairs. We validate the effectiveness of our method\nacross several datasets. Quantitative and qualitative evaluations illustrate\nthat our model outperforms other state-of-the-art methods in generating face\nsketches (or photos) with high visual quality and recognition ability.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/147","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T03:46:05Z","timestamp":1564285565000},"page":"1048-1054","source":"Crossref","is-referenced-by-count":24,"title":["Face Photo-Sketch Synthesis via Knowledge Transfer"],"prefix":"10.24963","author":[{"given":"Mingrui","family":"Zhu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an, China"},{"name":"School of Electronic Engineering, Xidian University, Xi'an, China"}]},{"given":"Nannan","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an, China"},{"name":"School of Telecommunications Engineering, Xidian University, Xi'an, China"}]},{"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an, China"},{"name":"School of Electronic Engineering, Xidian University, Xi'an, China"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an, China"},{"name":"School of Electronic Engineering, Xidian University, Xi'an, China"}]},{"given":"Zhifeng","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]}],"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":"2019-07-28T03:47:07Z","timestamp":1564285627000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/147"}},"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\/147","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}