Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss

Abstract

Filtering out unrealistic images from trained generative adversarial networks (GANs) has attracted considerable attention recently. Two density ratio based subsampling methods---Discriminator Rejection Sampling (DRS) and Metropolis-Hastings GAN (MH-GAN)---were recently proposed, and their effectiveness in improving GANs was demonstrated on multiple datasets. However, DRS and MH-GAN are based on discriminator based density ratio estimation (DRE) methods, so they may not work well if the discriminator in the trained GAN is far from optimal. Moreover, they do not apply to some GANs (e.g., MMD-GAN). In this paper, we propose a novel Softplus (SP) loss for DRE. Based on it, we develop a sample-based DRE method in a feature space learned by a specially designed and pre-trained ResNet-34 (DRE-F-SP). We derive the rate of convergence of a density ratio model trained under the SP loss. Then, we propose three different density ratio subsampling methods (DRE-F-SP+RS, DRE-F-SP+MH, and DRE-F-SP+SIR) for GANs based on DRE-F-SP. Our subsampling methods do not rely on the optimality of the discriminator and are suitable for all types of GANs. We empirically show our subsampling approach can substantially outperform DRS and MH-GAN on a synthetic dataset and the CIFAR-10 dataset, using multiple GANs.

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• 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
• Self-Attention Generative Adversarial Networks
• Rényi Divergence and Kullback-Leibler Divergence
• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Perceptual Adversarial Networks for Image-to-Image Transformation
• SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
• Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
• Generative Adversarial Nets from a Density Ratio Estimation Perspective
• Discriminator Rejection Sampling
• Deep density ratio estimation for change point detection

Cited by in corpus (6)

• Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression
• Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks
• Model Extraction and Defenses on Generative Adversarial Networks
• Generalized Energy Based Models
• Instance Selection for GANs
• Conditional Frechet Inception Distance