Methods › Computer Vision › Image Models › ResMLP
Residual Multi-Layer Perceptrons
ResMLP
Introduced by Hugo Touvron et al. in ResMLP: Feedforward networks for image classification with data-efficient training
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Residual Multi-Layer Perceptrons, or ResMLP, is an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a linear layer in which image patches interact, independently and identically across channels, and (ii) a two-layer feed-forward network in which channels interact independently per patch. At the end of the network, the patch representations are average pooled, and fed to a linear classifier.
Layer normalization is replaced with a simpler affine transformation, thanks to the absence of self-attention layers which makes training more stable. The affine operator is applied at the beginning ("pre-normalization") and end ("post-normalization") of each residual block. As a pre-normalization, Aff replaces LayerNorm without using channel-wise statistics. Initialization is achieved as α=1, and β=0. As a post-normalization, Aff is similar to LayerScale and α is initialized with the same small value.
Papers archive 2025-07-28
10 shown of 10, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Domain Influence in MRI Medical Image Segmentation: spatial versus k-space inputs 1 Jul 2024 · 1 repository · arXiv:2407.01367
-
Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network 1 Jul 2024 · 1 repository · arXiv:2407.01645Syntology ran 12 of 13 samples · 1 unverified
-
Compressing the Backward Pass of Large-Scale Neural Architectures by Structured Activation Pruning 28 Nov 2023 · 0 repositories · arXiv:2311.16883
-
NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement 20 Jun 2023 · 1 repository · arXiv:2306.11920
-
AutoInit: Automatic Initialization via Jacobian Tuning 27 Jun 2022 · 0 repositories · arXiv:2206.13568
-
Boosting Adversarial Transferability of MLP-Mixer 26 Apr 2022 · 0 repositories · arXiv:2204.12204
-
Hire-MLP: Vision MLP via Hierarchical Rearrangement 30 Aug 2021 · 10 repositories · arXiv:2108.13341Syntology ran 2 of 2 samples · 0 unverified · 1 pointer-only (licence)
-
S²-MLPv2: Improved Spatial-Shift MLP Architecture for Vision 2 Aug 2021 · 3 repositories · arXiv:2108.01072Syntology ran 4 of 4 samples · 0 unverified · 2 pointer-only (licence)
-
CycleMLP: A MLP-like Architecture for Dense Prediction 21 Jul 2021 · 8 repositories · arXiv:2107.10224Syntology ran 8 of 15 samples · 7 unverified · 1 pointer-only (licence)
-
ResMLP: Feedforward networks for image classification with data-efficient training 7 May 2021 · 19 repositories · arXiv:2105.03404Syntology ran 2 of 7 samples · 5 unverified
Tasks archive 2025-07-28
20 shown of 24 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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