RankGAN: A Maximum Margin Ranking GAN for Generating Faces
arXiv:1812.08196
Abstract
We present a new stage-wise learning paradigm for training generative adversarial networks (GANs). The goal of our work is to progressively strengthen the discriminator and thus, the generators, with each subsequent stage without changing the network architecture. We call this proposed method the RankGAN. We first propose a margin-based loss for the GAN discriminator. We then extend it to a margin-based ranking loss to train the multiple stages of RankGAN. We focus on face images from the CelebA dataset in our work and show visual as well as quantitative improvements in face generation and completion tasks over other GAN approaches, including WGAN and LSGAN.
Best Student Paper Award at Asian Conference on Computer Vision (ACCV), 2018 at Perth, Australia. Includes main paper and supplementary material. Total 32 pages including references
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Energy-based Generative Adversarial Network
- f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
- Neural Photo Editing with Introspective Adversarial Networks
- Least Squares Generative Adversarial Networks
- Boundary-Seeking Generative Adversarial Networks
- Stacked Generative Adversarial Networks
- Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking