Methods › Computer Vision › Image Models › gMLP

gMLP

7 papers tagged archive 2025-07-28

Introduced by Hanxiao Liu et al. in Pay Attention to MLPs

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

gMLP is an MLP-based alternative to Transformers without self-attention, which simply consists of channel projections and spatial projections with static parameterization. It is built out of basic MLP layers with gating. The model consists of a stack of L blocks with identical size and structure. Let X ∈ℝ^(n ×d) be the token representations with sequence length n and dimension d. Each block is defined as:

Z=σ(X U), Z̃=s(Z), Y=Z̃ V

where σ is an activation function such as GeLU. U and V define linear projections along the channel dimension - the same as those in the FFNs of Transformers (e.g., their shapes are 768 ×3072 and 3072 ×768 for BERT_(base)).

A key ingredient is s(·), a layer which captures spatial interactions. When s is an identity mapping, the above transformation degenerates to a regular FFN, where individual tokens are processed independently without any cross-token communication. One of the major focuses is therefore to design a good s capable of capturing complex spatial interactions across tokens. This leads to the use of a Spatial Gating Unit which involves a modified linear gating.

The overall block layout is inspired by inverted bottlenecks, which define s(·) as a spatial depthwise convolution. Note, unlike Transformers, gMLP does not require position embeddings because such information will be captured in s(·).

PaperSource

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 20 in the graph, strongest link: mentioned on GitHub). This answer is about arXiv:2105.08050, the paper the archive credits with this method.

Origin paper of this answer, arXiv:2105.08050 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 34 ran (of which 15 constructed an object rather than computing a result; 31 with no instrument failure: 1 honoured, 4 violated, 26 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified (of 44 harvested samples) · 11 pointer-only (licence). 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: 7 · with a code link: 4 · 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 7 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 7 of 7, 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 31 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
Instance Segmentation2
Object Detection2
Question Answering2
Semantic Segmentation2
object-detection2
All1
Classification1
Common Sense Reasoning1
Decoder1
Deep Learning1
Graph Representation Learning1
In-Context Learning1
Language Modeling1
Language Modelling1
Mixture-of-Experts1
Multi Label Text Classification1
Multi-Label Classification1
Multi-Label Text Classification1
Natural Language Inference1

Usage over time archive 2025-07-28

Papers per year tagged with gMLP: 2021 to 2022, peak 4 4 0 2021: 3 papers 2021 2022: 4 papers 2022
Papers per year the archive tags with this method, by the paper's archive date (7 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

Image Models

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