Methods › General › Attention Mechanisms › GALA

Global-and-Local attention

GALA

9 papers tagged archive 2025-07-28

Introduced by Drew Linsley et al. in Learning what and where to attend

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

Most attention mechanisms learn where to focus using only weak supervisory signals from class labels, which inspired Linsley et al. to investigate how explicit human supervision can affect the performance and interpretability of attention models. As a proof of concept, Linsley et al. proposed the global-and-local attention (GALA) module, which extends an SE block with a spatial attention mechanism.

Given the input feature map X, GALA uses an attention mask that combines global and local attention to tell the network where and on what to focus. As in SE blocks, global attention aggregates global information by global average pooling and then produces a channel-wise attention weight vector using a multilayer perceptron. In local attention, two consecutive 1×1 convolutions are conducted on the input to produce a positional weight map. The outputs of the local and global pathways are combined by addition and multiplication. Formally, GALA can be represented as: s_g = W₂ δ(W₁GAP(x))

sₗ = Conv₂^(1×1) (δ(Conv₁^(1×1)(X)))

s_g^* = Expand(s_g)

sₗ^* = Expand(sₗ)

s = tanh(a(s_g^* + sₗ^*) +m ·(s_g^* sₗ^*) )

Y = sX

where a,m ∈ℝ^C are learnable parameters representing channel-wise weight vectors.

Supervised by human-provided feature importance maps, GALA has significantly improved representational power and can be combined with any CNN backbone.

PaperSource

Papers archive 2025-07-28

9 shown of 9, 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

20 shown of 21 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 Generation1
3D geometry1
Deep Reinforcement Learning1
Diagnostic1
Domain Adaptation1
GPU1
GRAPH DOMAIN ADAPTATION1
General Knowledge1
Graph Learning1
Graph Neural Network1
Graph Representation Learning1
Image Categorization1
Object1
Object Recognition1
Out-of-Distribution Generalization1
Quantization1
Reinforcement Learning1
Reinforcement Learning (RL)1
Representation Learning1
Source-Free Domain Adaptation1

Usage over time archive 2025-07-28

Papers per year tagged with GALA: 2018 to 2025, peak 3 3 0 2018: 1 paper 2018 2019: 1 paper 2019 2020: 0 papers 2020 2021: 0 papers 2021 2022: 2 papers 2022 2023: 1 paper 2023 2024: 3 papers 2024 2025: 1 paper 2025
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

Attention Mechanisms

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