Methods › General › Attention Modules › Attention-augmented Convolution

Attention-augmented Convolution

3 papers tagged archive 2025-07-28

Introduced by Irwan Bello et al. in Attention Augmented Convolutional Networks

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

Attention-augmented Convolution is a type of convolution with a two-dimensional relative self-attention mechanism that can replace convolutions as a stand-alone computational primitive for image classification. It employs scaled-dot product attention and multi-head attention as with Transformers.

It works by concatenating convolutional and attentional feature map. To see this, consider an original convolution operator with kernel size k, Fᵢₙ input filters and Fₒᵤₜ output filters. The corresponding attention augmented convolution can be written as"

AAConv(X) = Concat[Conv(X), MHA(X)]

X originates from an input tensor of shape (H, W, Fᵢₙ). This is flattened to become X ∈ℝ^(HW ×Fᵢₙ) which is passed into a multi-head attention module, as well as a convolution (see above).

Similarly to the convolution, the attention augmented convolution 1) is equivariant to translation and 2) can readily operate on inputs of different spatial dimensions.

PaperSourceSee Code · leaderj1001/Attention-Augmented-Conv2d

Papers archive 2025-07-28

3 shown of 3, 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.

Tasks archive 2025-07-28

9 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
3D Point Cloud Classification1
General Classification1
Image Classification1
Music Modeling1
Music Tagging1
Object Detection1
Point Cloud Classification1
image-classification1
object-detection1

Usage over time archive 2025-07-28

Papers per year tagged with Attention-augmented Convolution: 2019 to 2024, peak 1 1 0 2019: 1 paper 2019 2020: 0 papers 2020 2021: 1 paper 2021 2022: 0 papers 2022 2023: 0 papers 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (3 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 ModulesConvolutions

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