Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data
arXiv:1711.10267
Abstract
In face-related applications with a public available dataset, synthesizing non-linear facial variations (e.g., facial expression, head-pose, illumination, etc.) through a generative model is helpful in addressing the lack of training data. In reality, however, there is insufficient data to even train the generative model for face synthesis. In this paper, we propose Differential Generative Adversarial Networks (D-GAN) that can perform photo-realistic face synthesis even when training data is small. Two discriminators are devised to ensure the generator to approximate a face manifold, which can express face changes as it wants. Experimental results demonstrate that the proposed method is robust to the amount of training data and synthesized images are useful to improve the performance of a face expression classifier.
arXiv comment20 pages
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Going Deeper in Facial Expression Recognition using Deep Neural Networks
- Energy-based Generative Adversarial Network
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Age Progression/Regression by Conditional Adversarial Autoencoder
- Deep generative-contrastive networks for facial expression recognition
- Semantic Image Inpainting with Deep Generative Models
- Neural Face Editing with Intrinsic Image Disentangling
- Mirror, mirror on the wall, tell me, is the error small?