Unsupervised Generation and Synthesis of Facial Images via an Auto-Encoder-Based Deep Generative Adversarial Network

Abstract

The processing of facial images is an important task, because it is required for a large number of real-world applications. As deep-learning models evolve, they require a huge number of images for training. In reality, however, the number of images available is limited. Generative adversarial networks (GANs) have thus been utilized for database augmentation, but they suffer from unstable training, low visual quality, and a lack of diversity. In this paper, we propose an auto-encoder-based GAN with an enhanced network structure and training scheme for Database (DB) augmentation and image synthesis. Our generator and decoder are divided into two separate modules that each take input vectors for low-level and high-level features; these input vectors affect all layers within the generator and decoder. The effectiveness of the proposed method is demonstrated by comparing it with baseline methods. In addition, we introduce a new scheme that can combine two existing images without the need for extra networks based on the auto-encoder structure of the discriminator in our model. We add a novel double-constraint loss to make the encoded latent vectors equal to the input vectors.

Special Issue on Intelligent Processing on Image and Optical Information

“…As the deep-learning model develops, a huge number of images is required for training. Jeong gi Kwak and Hanseok Ko [8] described in their article: 'Unsupervised Generation and Synthesis of Facial Images via an Auto-Encoder-Based Deep Generative Adversarial Network (GAN)' an auto-encoder-based GAN with an enhanced network structure and training scheme for database augmentation and image synthesis.…”

CDL-GAN: Contrastive Distance Learning Generative Adversarial Network for Image Generation

“…With multiple generators or discriminators, GANs can get more constructive gradient signals to learn intermediate representation. Larsen et al [8], Makhzani et al [9], Dumoulin et al [10], Wang, Xiaoqing [11], and Kwak, Jeong gi et al [12] use the most common encoder-decoder architecture to learn image features from latent space. These hybrid models are useful for addressing mode collapse.…”