Invertible Residual Networks

Understand

We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation.

• Typically, enforcing invertibility requires partitioning dimensions or restricting network architectures.
• In contrast, our approach only requires adding a simple normalization step during training, already available in standard frameworks.
• Invertible ResNets define a generative model which can be trained by maximum likelihood on unlabeled data.