Methods › Computer Vision › Convolutional Neural Networks › RevNet

RevNet

9 papers tagged archive 2025-07-28

Introduced by Aidan N. Gomez et al. in The Reversible Residual Network: Backpropagation Without Storing Activations

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

A Reversible Residual Network, or RevNet, is a variant of a ResNet 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. The result is a network architecture whose activation storage requirements are independent of depth, and typically at least an order of magnitude smaller compared with equally sized ResNets.

RevNets are composed of a series of reversible blocks. Units in each layer are partitioned into two groups, denoted x₁ and x₂; the authors find what works best is partitioning the channels. Each reversible block takes inputs (x₁, x₂) and produces outputs (y₁, y₂) according to the following additive coupling rules – inspired the transformation in NICE (nonlinear independent components estimation) – and residual functions F and G analogous to those in standard ResNets:

y₁ = x₁ + F(x₂) y₂ = x₂ + G(y₁)

Each layer’s activations can be reconstructed from the next layer’s activations as follows:

x₂ = y₂ − G(y₁) x₁ = y₁ − F(x₂)

Note that unlike residual blocks, reversible blocks must have a stride of 1 because otherwise the layer discards information, and therefore cannot be reversible. Standard ResNet architectures typically have a handful of layers with a larger stride. If we define a RevNet architecture analogously, the activations must be stored explicitly for all non-reversible layers.

PaperSourceSee Code · osmr/imgclsmob

In Syntology about another paper, arXiv:2601.08558: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: listed only). The lookup matched 'REVNET' ignoring case. About another paper: this answer is about arXiv:2601.08558, while the archive credits arXiv:1707.04585.

Origin paper of this answer, arXiv:2601.08558 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 9 · with a code link: 6 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2 of 9 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 9 of 9, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 32 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Classification3
image-classification3
Image Generation2
Attribute1
Classification1
Contrastive Learning1
Denoising1
Dimensionality Reduction1
Fine-Grained Image Classification1
General Classification1
Generative Adversarial Network1
Image Reconstruction1
Image Restoration1
Machine Translation1
Object1
Representation Learning1
Saliency Detection1
Segmentation1
Self-Supervised Image Classification1
Self-Supervised Learning1

Usage over time archive 2025-07-28

Papers per year tagged with RevNet: 2017 to 2023, peak 2 2 0 2017: 2 papers 2017 2018: 0 papers 2018 2019: 1 paper 2019 2020: 2 papers 2020 2021: 2 papers 2021 2022: 1 paper 2022 2023: 1 paper 2023
Papers per year the archive tags with this method, by the paper's archive date (9 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Convolutional Neural Networks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections