Wasserstein Introspective Neural Networks

Abstract

We present Wasserstein introspective neural networks (WINN) that are both a generator and a discriminator within a single model. WINN provides a significant improvement over the recent introspective neural networks (INN) method by enhancing INN's generative modeling capability. WINN has three interesting properties: (1) A mathematical connection between the formulation of the INN algorithm and that of Wasserstein generative adversarial networks (WGAN) is made. (2) The explicit adoption of the Wasserstein distance into INN results in a large enhancement to INN, achieving compelling results even with a single classifier --- e.g., providing nearly a 20 times reduction in model size over INN for unsupervised generative modeling. (3) When applied to supervised classification, WINN also gives rise to improved robustness against adversarial examples in terms of the error reduction. In the experiments, we report encouraging results on unsupervised learning problems including texture, face, and object modeling, as well as a supervised classification task against adversarial attacks.

arXiv commentAccepted to CVPR 2018 (Oral)

References in corpus (20)

• Adam: A Method for Stochastic Optimization
• Explaining and Harnessing Adversarial Examples
• Densely Connected Convolutional Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Improved Training of Wasserstein GANs
• Going Deeper with Convolutions
• Improved Techniques for Training GANs
• Searching for Activation Functions
• Deep Convolutional Inverse Graphics Network
• Adversarial Feature Learning
• Adversarially Learned Inference
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Layer Normalization
• Texture Synthesis Using Convolutional Neural Networks
• Aggregated Residual Transformations for Deep Neural Networks
• Adversarial Machine Learning at Scale
• $f$-divergence Inequalities
• A Theory of Generative ConvNet
• Deep Learning Face Attributes in the Wild
• Stacked Generative Adversarial Networks

Cited by in corpus (1)

• Learning Energy-based Spatial-Temporal Generative ConvNets for Dynamic Patterns