Two Birds with One Stone: Iteratively Learn Facial Attributes with GANs
share
Generating high fidelity identity-preserving faces has a wide range of applications. Although a number of generative models have been developed to tackle this problem, it is still far from satisfying. Recently, Generative adversarial network (GAN) has shown great potential for generating or transforming images of exceptional visual fidelity. In this paper, we propose to train GAN iteratively via regularizing the minmax process with an integrated loss, which includes not only the per-pixel loss but also the perceptual loss. We argue that the perceptual information benefits the output of a high-quality image, while preserving the identity information. In contrast to the existing methods only deal with either image generation or transformation, our proposed iterative architecture can achieve both of them. Experiments on the multi-label facial dataset CelebA demonstrate that the proposed model has excellent performance on recognizing multiple attributes, generating a high-quality image, and transforming image with controllable attributes.
READ FULL TEXT
