Learning Implicit Generative Models by Matching Perceptual Features
This addresses the challenge of efficient and stable generative modeling for AI/ML researchers, though it is incremental as it builds on existing moment matching methods.
The paper tackles the problem of learning implicit generative models by proposing a moment matching approach that uses perceptual features from pretrained ConvNets, achieving state-of-the-art results on challenging benchmarks.
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.