Modular Generative Adversarial Networks

被引:38
作者
Zhao, Bo [1 ]
Chang, Bo [1 ]
Jie, Zequn [2 ]
Sigal, Leonid [1 ]
机构
[1] Univ British Columbia, Vancouver, BC, Canada
[2] Tencent AI Lab, Bellevue, WA USA
来源
COMPUTER VISION - ECCV 2018, PT XIV | 2018年 / 11218卷
基金
加拿大自然科学与工程研究理事会;
关键词
Neural modular network; Generative adversarial network; Image generation; Image translation;
D O I
10.1007/978-3-030-01264-9_10
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Existing methods for multi-domain image-to-image translation (or generation) attempt to directly map an input image (or a random vector) to an image in one of the output domains. However, most existing methods have limited scalability and robustness, since they require building independent models for each pair of domains in question. This leads to two significant shortcomings: (1) the need to train exponential number of pairwise models, and (2) the inability to leverage data from other domains when training a particular pairwise mapping. Inspired by recent work on module networks, this paper proposes ModularGAN for multi-domain image generation and image-to-image translation. ModularGAN consists of several reusable and composable modules that carry on different functions (e.g., encoding, decoding, transformations). These modules can be trained simultaneously, leveraging data from all domains, and then combined to construct specific GAN networks at test time, according to the specific image translation task. This leads to ModularGAN's superior flexibility of generating (or translating to) an image in any desired domain. Experimental results demonstrate that our model not only presents compelling perceptual results but also outperforms state-of-the-art methods on multi-domain facial attribute transfer.
引用
收藏
页码:157 / 173
页数:17
相关论文
共 34 条
[1]   Neural Module Networks [J].
Andreas, Jacob ;
Rohrbach, Marcus ;
Darrell, Trevor ;
Klein, Dan .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :39-48
[2]  
[Anonymous], 2016, ARXIV161005586
[3]  
[Anonymous], 2016, P 2016 C N AM CHAPT, DOI DOI 10.18653/V1/N16-1181
[4]  
[Anonymous], 2016, NIPS WORKSH ADV TRAI
[5]  
Arjovsky M, 2017, PR MACH LEARN RES, V70
[6]  
Chang Bo, 2018, WACV
[7]   StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation [J].
Choi, Yunjey ;
Choi, Minje ;
Kim, Munyoung ;
Ha, Jung-Woo ;
Kim, Sunghun ;
Choo, Jaegul .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :8789-8797
[8]  
Goodfellow I., 2014, P ADV NEUR INF PROC, DOI [10.48550/arXiv.1406.2661, DOI 10.48550/ARXIV.1406.2661]
[9]  
Gulrajani F., 2017, ADV NEURAL INFORM PR, V30, P5768, DOI DOI 10.5555/3295222.3295327
[10]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778