Adaptive Weighted Discriminator for Training Generative Adversarial Networks

Abstract

Generative adversarial network (GAN) has become one of the most important neural network models for classical unsupervised machine learning. A variety of discriminator loss functions have been developed to train GAN's discriminators and they all have a common structure: a sum of real and fake losses that only depends on the actual and generated data respectively. One challenge associated with an equally weighted sum of two losses is that the training may benefit one loss but harm the other, which we show causes instability and mode collapse. In this paper, we introduce a new family of discriminator loss functions that adopts a weighted sum of real and fake parts, which we call adaptive weighted loss functions or aw-loss functions. Using the gradients of the real and fake parts of the loss, we can adaptively choose weights to train a discriminator in the direction that benefits the GAN's stability. Our method can be potentially applied to any discriminator model with a loss that is a sum of the real and fake parts. Experiments validated the effectiveness of our loss functions on an unconditional image generation task, improving the baseline results by a significant margin on CIFAR-10, STL-10, and CIFAR-100 datasets in Inception Scores and FID.

arXiv comment16 pages total, 7 figures, 6 tables and 2 algorithms

References in corpus (15)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Which Training Methods for GANs do actually Converge?
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Unrolled Generative Adversarial Networks
• Mode Regularized Generative Adversarial Networks
• The Numerics of GANs
• Demystifying MMD GANs
• Dual Discriminator Generative Adversarial Nets
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• On the Limitations of First-Order Approximation in GAN Dynamics
• Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game
• Smoothness and Stability in GANs