cGANs with Multi-Hinge Loss
arXiv:1912.04216
Abstract
We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings. We study the compromise between training a state of the art generator and an accurate classifier simultaneously, and propose a way to use our algorithm to measure the degree to which a generator and critic are class conditional. We show the trade-off between a generator-critic pair respecting class conditioning inputs and generating the highest quality images. With our multi-hinge loss modification we are able to improve Inception Scores and Frechet Inception Distance on the Imagenet dataset. We make our tensorflow code available at https://github.com/ilyakava/gan.
arXiv commentAccepted to Winter Conference on Applications of Computer Vision (WACV) 2021
References in corpus (19)
- Conditional Generative Adversarial Nets
- Deep Residual Learning for Image Recognition
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Spectral Normalization for Generative Adversarial Networks
- Self-Attention Generative Adversarial Networks
- Generative Adversarial Text to Image Synthesis
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- A Learned Representation For Artistic Style
- Semi-Supervised Learning with Generative Adversarial Networks
- MMD GAN: Towards Deeper Understanding of Moment Matching Network
- Modulating early visual processing by language
- Triple Generative Adversarial Nets
- Dual Discriminator Generative Adversarial Nets
- High-Fidelity Image Generation With Fewer Labels
- Geometric GAN
- Semi-supervised Conditional GANs
- Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game
- Class-Splitting Generative Adversarial Networks
Cited by in corpus (6)
- Training Generative Adversarial Networks with Limited Data
- Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
- Score-Guided Generative Adversarial Networks
- Omni-GAN: On the Secrets of cGANs and Beyond
- S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
- Physical Context and Timing Aware Sequence Generating GANs