i-RevNet: Deep Invertible Networks

Understand

It is widely believed that the success of deep convolutional networks is based on progressively discarding uninformative variability about the input with respect to the problem at hand.

• This is supported empirically by the difficulty of recovering images from their hidden representations, in most commonly used network architectures.
• In this paper we show via a one-to-one mapping that this loss of information is not a necessary condition to learn representations that generalize well on complicated problems, such as ImageNet.
• Via a cascade of homeomorphic layers, we build the i-RevNet, a network that can be fully inverted up to the final projection onto the classes, i.e.