HackerPapers

arXiv:1707.04585cs.CV

The Reversible Residual Network: Backpropagation Without Storing Activations

Aidan N. Gomez, Mengye Ren, Raquel Urtasun, Roger B. Grosse

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.

arXiv comments
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition cs.LGMachine Learning

On Hacker News

Linked by 2 identifiable commenters in 2 comments across 2 threads, from Jul 2017 to Dec 2020.

Comments linking this paper, per year.

Discussed in comments2 threads

  1. Researchers propose faster, more efficient alternatives to backpropagation 1 comment

    • There's also RevNets, which saves memory by only using reversible layers: https://arxiv.org/abs/1707.04585

      kliptView on HNParent context

  2. The future of deep learning 1 comment

    • Yep, that's the one. By the way, this "local-changes-only" approach crops up in many other places too. In CS and nature, because it's just so damn energy-efficient. For example, check out this (recent, July 2017) paper: Gomez, Ren, Urtasun & Grosse: "The Reversible Residual…

      RadimView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.