Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
arXiv:1807.11346
Abstract
We propose to incorporate adversarial dropout in generative multi-adversarial networks, by omitting or dropping out, the feedback of each discriminator in the framework with some probability at the end of each batch. Our approach forces the single generator not to constrain its output to satisfy a single discriminator, but, instead, to satisfy a dynamic ensemble of discriminators. We show that this leads to a more generalized generator, promoting variety in the generated samples and avoiding the common mode collapse problem commonly experienced with generative adversarial networks (GANs). We further provide evidence that the proposed framework, named Dropout-GAN, promotes sample diversity both within and across epochs, eliminating mode collapse and stabilizing training.
arXiv commentExtended version of ACM KDD'18 Deep Learning Day
References in corpus (16)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Improving neural networks by preventing co-adaptation of feature detectors
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Improved Techniques for Training GANs
- Energy-based Generative Adversarial Network
- MMD GAN: Towards Deeper Understanding of Moment Matching Network
- Unrolled Generative Adversarial Networks
- Mode Regularized Generative Adversarial Networks
- On Convergence and Stability of GANs
- Stabilizing Training of Generative Adversarial Networks through Regularization
- Dual Discriminator Generative Adversarial Nets
- Stabilizing GAN Training with Multiple Random Projections
- CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning
- An empirical analysis of dropout in piecewise linear networks
- Multi-Generator Generative Adversarial Nets
- Message Passing Multi-Agent GANs
Cited by in corpus (6)
- StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis
- Controllable Person Image Synthesis with Attribute-Decomposed GAN
- CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
- HumanGAN: A Generative Model of Humans Images
- Prb-GAN: A Probabilistic Framework for GAN Modelling
- Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification