RankGAN: A Maximum Margin Ranking GAN for Generating Faces

By Rahul Dey, Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides. 2018

24 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Anna Khoreva
2. Edgar Schönfeld
3. Bernt Schiele
4. Luc Van Gool
5. Ming-Hsuan Yang
6. Philip H. S. Torr
7. Xiaogang Wang
8. Jitendra Malik

In Generative Models

1. Anna Khoreva
2. Bernt Schiele
3. Edgar Schönfeld
4. Zhangyang Wang
5. Shiyu Chang
6. Prateek Katiyar
7. Chao Dong

Citations in the corpus

• A U-Net Based Discriminator for Generative Adversarial Networks (2020, background): “GAN [14] and its conditional variant [33] have recently demonstrated impressive results on different computer vision tasks, including image synthesis [38, 50, 19, 5, 20, 27, 10].”