O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks

Understand

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.