Normalized Diversification

Abstract

Generating diverse yet specific data is the goal of the generative adversarial network (GAN), but it suffers from the problem of mode collapse. We introduce the concept of normalized diversity which force the model to preserve the normalized pairwise distance between the sparse samples from a latent parametric distribution and their corresponding high-dimensional outputs. The normalized diversification aims to unfold the manifold of unknown topology and non-uniform distribution, which leads to safe interpolation between valid latent variables. By alternating the maximization over the pairwise distance and updating the total distance (normalizer), we encourage the model to actively explore in the high-dimensional output space. We demonstrate that by combining the normalized diversity loss and the adversarial loss, we generate diverse data without suffering from mode collapsing. Experimental results show that our method achieves consistent improvement on unsupervised image generation, conditional image generation and hand pose estimation over strong baselines.

12 pages, 9 figures, to appear in CVPR 2019

References in corpus (8)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Spectral Normalization for Generative Adversarial Networks
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor
• Training generative neural networks via Maximum Mean Discrepancy optimization
• 3D Hand Pose Tracking and Estimation Using Stereo Matching
• BourGAN: Generative Networks with Metric Embeddings