Learning Implicit Generative Models by Matching Perceptual Features

TL;DR

This paper introduces a novel moment matching approach using perceptual features from pretrained ConvNets to learn implicit generative models, outperforming existing methods on challenging benchmarks.

Contribution

It proposes a new moment matching method leveraging perceptual features, avoiding adversarial training and online kernel learning, with improved efficiency and state-of-the-art results.

Findings

Achieves state-of-the-art results on benchmark datasets.

Improves efficiency by reducing required moments and minibatch size.

Avoids adversarial training and online kernel learning complexities.

Abstract

Perceptual features (PFs) have been used with great success in tasks such as transfer learning, style transfer, and super-resolution. However, the efficacy of PFs as key source of information for learning generative models is not well studied. We investigate here the use of PFs in the context of learning implicit generative models through moment matching (MM). More specifically, we propose a new effective MM approach that learns implicit generative models by performing mean and covariance matching of features extracted from pretrained ConvNets. Our proposed approach improves upon existing MM methods by: (1) breaking away from the problematic min/max game of adversarial learning; (2) avoiding online learning of kernel functions; and (3) being efficient with respect to both number of used moments and required minibatch size. Our experimental results demonstrate that, due to the expressiveness of PFs from pretrained deep ConvNets, our method achieves state-of-the-art results for challenging benchmarks.