标题：Sparsely grouped multi-task generative adversarial networks for facial attribute manipulation
作者：Zhang, Jichao ;Cao, Gongze ;Shu, Yezhi ;Zhong, Fan ;Liu, Meng ;Xu, Songhua ;Qin, Xueying
作者机构：[Zhang, Jichao ] School of Computer Science and Technology, Shandong University, China;[Shu, Yezhi ;Qin, Xueying ] School of Software, Shandong Univer 更多
会议名称：26th ACM Multimedia conference, MM 2018
会议日期：22 October 2018 through 26 October 2018
来源：MM 2018 - Proceedings of the 2018 ACM Multimedia Conference
关键词：Deep Learning; Generative Adversarial Networks; Image Translation
摘要：Recently, Image-to-Image Translation (IIT) has achieved great progress in image style transfer and semantic context manipulation for images. However, existing approaches require exhaustively labelling training data, which is labor demanding, difficult to scale up, and hard to adapt to a new domain. To overcome such a key limitation, we propose Sparsely Grouped Generative Adversarial Networks (SG-GAN) as a novel approach that can translate images in sparsely grouped datasets where only a few train samples are labelled. Using a one-input multi-output architecture, SG-GAN is well-suited for tackling multi-task learning and sparsely grouped learning tasks. The new model is able to translate images among multiple groups using only a single trained model. To experimentally validate the advantages of the new model, we apply the proposed method to tackle a series of attribute manipulation tasks for facial images as a case study. Experimental results show that SG-GAN can achieve comparable results with state-of-the-art methods on adequately labelled datasets while attaining a superior image translation quality on sparsely grouped datasets. © 2018 Copyright held by the owner/author(s). Publication rights licensed to the Association for Computing Machinery.