LDMGAN: Reducing Mode Collapse in GANs with Latent Distribution Matching

Zhiwen Zuo, Lei Zhao, Huiming Zhang, Qihang Mo, Haibo Chen, Zhizhong Wang, AiLin Li, Lihong Qiu, Wei Xing, Dongming Lu

Keywords: Deep Learning, Unsupervised Learning, Generative Adversarial Networks, Mode Collapse, AutoEncoder

TL;DR: We propose an AE-based GAN that alleviates mode collapse in GANs.

Abstract: Generative Adversarial Networks (GANs) have shown impressive results in modeling distributions over complicated manifolds such as those of natural images. However, GANs often suffer from mode collapse, which means they are prone to characterize only a single or a few modes of the data distribution. In order to address this problem, we propose a novel framework called LDMGAN. We first introduce Latent Distribution Matching (LDM) constraint which regularizes the generator by aligning distribution of generated samples with that of real samples in latent space. To make use of such latent space, we propose a regularized AutoEncoder (AE) that maps the data distribution to prior distribution in encoded space. Extensive experiments on synthetic data and real world datasets show that our proposed framework significantly improves GAN’s stability and diversity.

Data: [Stacked MNIST](https://paperswithcode.com/dataset/stacked-mnist)