Omni-GAN: On the Secrets of cGANs and Beyond

11/26/2020

∙

It has been an important problem to design a proper discriminator for conditional generative adversarial networks (cGANs). In this paper, we investigate two popular choices, the projection-based and classification-based discriminators, and reveal that both of them suffer some kind of drawbacks that affect the learning ability of cGANs. Then, we present our solution that trains a powerful discriminator and avoids over-fitting with regularization. In addition, we unify multiple targets (class, domain, reality, etc.) into one loss function to enable a wider range of applications. Our algorithm, named Omni-GAN, achieves competitive performance on a few popular benchmarks. More importantly, Omni-GAN enjoys both high generation quality and low risks in mode collapse, offering new possibilities for optimizing cGANs.Code is available at <https://github.com/PeterouZh/Omni-GAN-PyTorch>.

READ FULL TEXT

Omni-GAN: On the Secrets of cGANs and Beyond

Adaptive DropBlock Enhanced Generative Adversarial Networks for Hyperspectral Image Classification

BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network

Improving GAN with neighbors embedding and gradient matching

Probabilistic Generative Adversarial Networks

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better

cGANs with Multi-Hinge Loss

Adversarial Fisher Vectors for Unsupervised Representation Learning

Omni-GAN: On the Secrets of cGANs and Beyond

Related Research

Adaptive DropBlock Enhanced Generative Adversarial Networks for Hyperspectral Image Classification

BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network

Improving GAN with neighbors embedding and gradient matching

Probabilistic Generative Adversarial Networks

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better

cGANs with Multi-Hinge Loss

Adversarial Fisher Vectors for Unsupervised Representation Learning