Methods › General › Attention Modules › Re-Attention Module

Re-Attention Module

4 papers tagged archive 2025-07-28

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

The Re-Attention Module is an attention layer used in the DeepViT architecture which mixes the attention map with a learnable matrix before multiplying with the values. The motivation is to re-generate the attention maps to increase their diversity at different layers with negligible computation and memory cost. The authors note that traditional self-attention fails to learn effective concepts for representation learning in deeper layers of ViT -- attention maps become more similar and less diverse in deeper layers (attention collapse) - and this hinders the model from getting expected performance gain. Re-attention is implemented by:

Re-Attention(Q, K, V)=Norm(Θ^⊤(Softmax((Q K^⊤)/(√(d))))) V

where transformation matrix Θ is multiplied to the self-attention map A along the head dimension.

Source: DeepViT: Towards Deeper Vision Transformer

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Attention-ResUNet; Repulsive Attention; Reinforced Attention; Relational Attention; SVD-Inspired Attention; Re-Attention Mechanism; reverse cross-attention; Subtree Attention (STA).

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: 4 · with a code link: 1 · where Syntology ran a sample: 1 (1 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 (1 of 4 tagged: 1 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 4 of 4, 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

8 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 Classification1
Point Cloud Segmentation1
Representation Learning1
Segmentation1
Semantic Segmentation1
Visual Commonsense Reasoning1
Visual Reasoning1
image-classification1

Usage over time archive 2025-07-28

Papers per year tagged with Re-Attention Module: 2021 to 2024, peak 2 2 0 2021: 1 paper 2021 2022: 0 papers 2022 2023: 2 papers 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (4 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

Attention Modules

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