Normalized Diversification
This addresses the mode collapse issue in GANs for researchers and practitioners in generative modeling, offering an incremental improvement over existing methods.
The paper tackles the mode collapse problem in generative adversarial networks (GANs) by introducing normalized diversification to preserve pairwise distances between latent samples and outputs, enabling safe interpolation and diverse data generation. Experimental results show consistent improvements in unsupervised image generation, conditional image generation, and hand pose estimation over strong baselines.
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.