Generative Feature Matching Networks

Cicero Nogueira dos Santos, Inkit Padhi, Pierre Dognin, Youssef Mroueh

Abstract: We propose a non-adversarial feature matching-based approach to train generative models. Our approach, Generative Feature Matching Networks (GFMN), leverages pretrained neural networks such as autoencoders and ConvNet classifiers to perform feature extraction. We perform an extensive number of experiments with different challenging datasets, including ImageNet. Our experimental results demonstrate that, due to the expressiveness of the features from pretrained ImageNet classifiers, even by just matching first order statistics, our approach can achieve state-of-the-art results for challenging benchmarks such as CIFAR10 and STL10.

Keywords: Generative Deep Neural Networks, Feature Matching, Maximum Mean Discrepancy, Generative Adversarial Networks

TL;DR: A new non-adversarial feature matching-based approach to train generative models that achieves state-of-the-art results.

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CelebA](https://paperswithcode.com/dataset/celeba), [MNIST](https://paperswithcode.com/dataset/mnist), [STL-10](https://paperswithcode.com/dataset/stl-10)