Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE

Abstract

Wasserstein autoencoder (WAE) shows that matching two distributions is equivalent to minimizing a simple autoencoder (AE) loss under the constraint that the latent space of this AE matches a pre-specified prior distribution. This latent space distribution matching is a core component of WAE, and a challenging task. In this paper, we propose to use the contrastive learning framework that has been shown to be effective for self-supervised representation learning, as a means to resolve this problem. We do so by exploiting the fact that contrastive learning objectives optimize the latent space distribution to be uniform over the unit hyper-sphere, which can be easily sampled from. We show that using the contrastive learning framework to optimize the WAE loss achieves faster convergence and more stable optimization compared with existing popular algorithms for WAE. This is also reflected in the FID scores on CelebA and CIFAR-10 datasets, and the realistic generated image quality on the CelebA-HQ dataset.

References in corpus (9)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• A Simple Framework for Contrastive Learning of Visual Representations
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Bootstrap your own latent: A new approach to self-supervised Learning
• Towards Principled Methods for Training Generative Adversarial Networks
• Mode Regularized Generative Adversarial Networks
• Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
• Towards Deeper Understanding of Variational Autoencoding Models
• From optimal transport to generative modeling: the VEGAN cookbook