GMM-Based Generative Adversarial Encoder Learning
arXiv:2012.04525
Abstract
While GAN is a powerful model for generating images, its inability to infer a latent space directly limits its use in applications requiring an encoder. Our paper presents a simple architectural setup that combines the generative capabilities of GAN with an encoder. We accomplish this by combining the encoder with the discriminator using shared weights, then training them simultaneously using a new loss term. We model the output of the encoder latent space via a GMM, which leads to both good clustering using this latent space and improved image generation by the GAN. Our framework is generic and can be easily plugged into any GAN strategy. In particular, we demonstrate it both with Vanilla GAN and Wasserstein GAN, where in both it leads to an improvement in the generated images in terms of both the IS and FID scores. Moreover, we show that our encoder learns a meaningful representation as its clustering results are competitive with the current GAN-based state-of-the-art in clustering.
References in corpus (13)
- Conditional Generative Adversarial Nets
- 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
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Adversarially Learned Inference
- MaskGAN: Better Text Generation via Filling in the______
- Clustering with Deep Learning: Taxonomy and New Methods
- Texture Synthesis with Spatial Generative Adversarial Networks
- Improving MMD-GAN Training with Repulsive Loss Function
- Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images
- AGAN: Towards Automated Design of Generative Adversarial Networks
- Quick and Easy Time Series Generation with Established Image-based GANs