Mode Regularized Generative Adversarial Networks
arXiv:1612.02136
Abstract
Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue that these bad behaviors of GANs are due to the very particular functional shape of the trained discriminators in high dimensional spaces, which can easily make training stuck or push probability mass in the wrong direction, towards that of higher concentration than that of the data generating distribution. We introduce several ways of regularizing the objective, which can dramatically stabilize the training of GAN models. We also show that our regularizers can help the fair distribution of probability mass across the modes of the data generating distribution, during the early phases of training and thus providing a unified solution to the missing modes problem.
Published as a conference paper at ICLR 2017
References in corpus (3)
Cited by in corpus (14)
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
- Dual Discriminator Generative Adversarial Nets
- Adversarial Generation of Natural Language
- Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs
- Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
- Learning Generative Models across Incomparable Spaces
- Distributional Adversarial Networks
- PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain
- Recent Advances of Image Steganography with Generative Adversarial Networks
- Hindsight Generative Adversarial Imitation Learning
- Adversarial Sub-sequence for Text Generation
- IVE-GAN: Invariant Encoding Generative Adversarial Networks
- A Study of Cross-domain Generative Models applied to Cartoon Series