O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
arXiv:1903.01931
Abstract
In this paper, we propose Orthogonal Generative Adversarial Networks (O-GANs). We decompose the network of discriminator orthogonally and add an extra loss into the objective of common GANs, which can enforce discriminator become an effective encoder. The same extra loss can be embedded into any kind of GANs and there is almost no increase in computation. Furthermore, we discuss the principle of our method, which is relative to the fully-exploiting of the remaining degrees of freedom of discriminator. As we know, our solution is the simplest approach to train a generative adversarial network with auto-encoding ability.
References in corpus (15)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Improved Training of Wasserstein GANs
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Adversarial Feature Learning
- Adversarially Learned Inference
- Autoencoding beyond pixels using a learned similarity metric
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Stabilizing Training of Generative Adversarial Networks through Regularization
- IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
- Maximum Entropy Generators for Energy-Based Models
- Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
- GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint