CMOS-GAN: Semi-Supervised Generative Adversarial Model for Cross-Modality Face Image Synthesis

doi:10.1109/TIP.2022.3226413

	CMOS-GAN: Semi-Supervised Generative Adversarial Model for Cross-Modality Face Image Synthesis
	Yu, Shikang 1,2; Han, Hu 1,2,3; Shan, Shiguang 1,2,3; Chen, Xilin 1,2
	2023
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	32 页码:144-158
摘要	Cross-modality face image synthesis such as sketch-to-photo, NIR-to-RGB, and RGB-to-depth has wide applications in face recognition, face animation, and digital entertainment. Conventional cross-modality synthesis methods usually require paired training data, i.e., each subject has images of both modalities. However, paired data can be difficult to acquire, while unpaired data commonly exist. In this paper, we propose a novel semi-supervised cross-modality synthesis method (namely CMOS-GAN), which can leverage both paired and unpaired face images to learn a robust cross-modality synthesis model. Specifically, CMOS-GAN uses a generator of encoder-decoder architecture for new modality synthesis. We leverage pixel-wise loss, adversarial loss, classification loss, and face feature loss to exploit the information from both paired multi-modality face images and unpaired face images for model learning. In addition, since we expect the synthetic new modality can also be helpful for improving face recognition accuracy, we further use a modified triplet loss to retain the discriminative features of the subject in the synthetic modality. Experiments on three cross-modality face synthesis tasks (NIR-to-VIS, RGB-to-depth, and sketch-to-photo) show the effectiveness of the proposed approach compared with the state-of-the-art. In addition, we also collect a large-scale RGB-D dataset (VIPL-MumoFace-3K) for the RGB-to-depth synthesis task. We plan to open-source our code and VIPL-MumoFace-3K dataset to the community (https://github.com/skgyu/CMOS-GAN).
关键词	Cross-modality synthesis semi-supervised synthesis cross-modality face recognition generative adversarial networks
DOI	10.1109/TIP.2022.3226413
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFA0700804] ; National Natural Science Foundation of China[61732004] ; National Natural Science Foundation of China[62176249]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000902111900011
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：5[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/20152
专题	中国科学院计算技术研究所期刊论文
通讯作者	Han, Hu
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Peng Cheng Lab, Shenzhen 518055, Peoples R China
推荐引用方式 GB/T 7714	Yu, Shikang,Han, Hu,Shan, Shiguang,et al. CMOS-GAN: Semi-Supervised Generative Adversarial Model for Cross-Modality Face Image Synthesis[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2023,32:144-158.
APA	Yu, Shikang,Han, Hu,Shan, Shiguang,&Chen, Xilin.(2023).CMOS-GAN: Semi-Supervised Generative Adversarial Model for Cross-Modality Face Image Synthesis.IEEE TRANSACTIONS ON IMAGE PROCESSING,32,144-158.
MLA	Yu, Shikang,et al."CMOS-GAN: Semi-Supervised Generative Adversarial Model for Cross-Modality Face Image Synthesis".IEEE TRANSACTIONS ON IMAGE PROCESSING 32(2023):144-158.