Wasserstein Divergence GAN With Cross-Age Identity Expert and Attribute Retainer for Facial Age Transformation
| Autor: | Rui-Cang Xie, Gee-Sern Hsu, Zhi-Ting Chen |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
General Computer Science
Computer science Feature extraction 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Facial recognition system facial age transformation Identity preservation 0202 electrical engineering electronic engineering information engineering General Materials Science Divergence (statistics) 0105 earth and related environmental sciences Retainer business.industry General Engineering Transformation (function) Benchmark (computing) Identity (object-oriented programming) 020201 artificial intelligence & image processing lcsh:Electrical engineering. Electronics. Nuclear engineering Artificial intelligence Generative adversarial network business lcsh:TK1-9971 computer face recognition |
| Zdroj: | IEEE Access, Vol 9, Pp 39695-39706 (2021) |
| ISSN: | 2169-3536 |
| DOI: | 10.1109/access.2021.3062499 |
| Popis: | We propose the Wasserstein Divergence GAN with an identity expert and an attribute retainer for facial age transformation. The Wasserstein Divergence GAN (WGAN-div) can better stabilize the training and lead to better target image generation. The identity expert aims to preserve the input identity at output, and the attribute retainer aims to preserve the input attribute at output. Unlike the previous works which take a specific model for identity and attribute preservation without giving a reason, both the identity expert and the attribute retainer in our proposed model are determined from a comprehensive comparison study on the state-of-the-art pretrained models. The candidate networks considered for identity preservation include the VGG-Face, VGG-Face2, LightCNN and ArcFace. The candidate backbones for making the attribute retainer are the VGG-Face, VGG-Object and DEX networks. This study offers a guidebook for choosing the appropriate modules for identity and attribute preservation. The interactions between the identity expert and attribute retainer are also extensively studied and experimented. To further enhance the performance, we augment the data by the 3DMM and explore the advantages of the additional training on cross-age datasets. The additional cross-age training is validated to make the identity expert capable of handling cross-age face recognition. The performance of our approach is justified by the desired age transformation with identity well preserved. Experiments on benchmark databases show that the proposed approach is highly competitive to state-of-the-art methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|