Methods › General › Attention Mechanisms › GALA
Global-and-Local attention
GALA
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.
In Syntology about another paper, arXiv:2401.12979: no code under this exact name (no_code; paper_only). About another paper: this answer is about arXiv:2401.12979, while the archive credits arXiv:1805.08819, so it does not say whether this method has code.
From the lookup's note on this name: The same name also belongs to the paper “GALA: Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networks” (arXiv:2105.01827, 77 citations), which the lookup finds cited far more than the paper this answer is about (33 citations), so this answer may be about a different sense of the name. For arXiv:2105.01827: ask the lookup about it.
Origin paper of this answer, arXiv:2401.12979 (its page on Syntology).
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: 9 · with a code link: 4 · 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 9 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 9 of 9, 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.
-
Online Learning-guided Learning Rate Adaptation via Gradient Alignment 10 Jun 2025 · 0 repositories · arXiv:2506.08419
-
GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation 22 Oct 2024 · 1 repository · arXiv:2410.16606
-
GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation 13 Oct 2024 · 0 repositories · arXiv:2410.10037
-
GALA: Generating Animatable Layered Assets from a Single Scan 23 Jan 2024 · 0 repositories · arXiv:2401.12979
-
Does Invariant Graph Learning via Environment Augmentation Learn Invariance? 29 Oct 2023 · 1 repository · arXiv:2310.19035Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows 17 Oct 2022 · 0 repositories · arXiv:2210.08737
-
GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing 31 Mar 2022 · 0 repositories · arXiv:2204.00125
-
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning 9 Jun 2019 · 1 repository · arXiv:1906.04585
-
Learning what and where to attend 22 May 2018 · 1 repository · arXiv:1805.08819
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.
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