The Reversible Residual Network: Backpropagation Without Storing Activations

TL;DR

The paper introduces Reversible Residual Networks (RevNets), which enable backpropagation without storing activations, significantly reducing memory usage while maintaining high classification accuracy on standard datasets.

Contribution

The paper proposes RevNets that reconstruct activations during backpropagation, eliminating the need to store them and addressing memory bottlenecks in deep residual networks.

Findings

RevNets achieve similar accuracy to traditional ResNets on CIFAR and ImageNet.

Memory requirements are independent of network depth in RevNets.

RevNets enable training of deeper networks with less memory.

Abstract

Deep residual networks (ResNets) have significantly pushed forward the state-of-the-art on image classification, increasing in performance as networks grow both deeper and wider. However, memory consumption becomes a bottleneck, as one needs to store the activations in order to calculate gradients using backpropagation. We present the Reversible Residual Network (RevNet), a variant of ResNets where each layer's activations can be reconstructed exactly from the next layer's. Therefore, the activations for most layers need not be stored in memory during backpropagation. We demonstrate the effectiveness of RevNets on CIFAR-10, CIFAR-100, and ImageNet, establishing nearly identical classification accuracy to equally-sized ResNets, even though the activation storage requirements are independent of depth.