Methods › General › Attention Mechanisms › RGA

Relation-aware Global Attention

RGA

11 papers tagged archive 2025-07-28

Introduced by Zhizheng Zhang et al. in Relation-Aware Global Attention for Person Re-identification

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

In relation-aware global attention (RGA) stresses the importance of global structural information provided by pairwise relations, and uses it to produce attention maps.

RGA comes in two forms, spatial RGA (RGA-S) and channel RGA (RGA-C). RGA-S first reshapes the input feature map X to C×(H×W) and the pairwise relation matrix R ∈ℝ^((H×W)×(H×W)) is computed using Q = δ(W^QX) K = δ(WᴷX) R = QᵀK The relation vector rᵢ at position i is defined by stacking pairwise relations at all positions: rᵢ = [R(i, :); R(:,i)] and the spatial relation-aware feature yᵢ can be written as Yᵢ = [gᶜ_(avg)(δ(W^φ xᵢ)); δ(W^ϕ rᵢ)] where gᶜ_(avg) denotes global average pooling in the channel domain. Finally, the spatial attention score at position i is given by aᵢ = σ(W₂δ(W₁yᵢ)) RGA-C has the same form as RGA-S, except for taking the input feature map as a set of H×W-dimensional features.

RGA uses global relations to generate the attention score for each feature node, so provides valuable structural information and significantly enhances the representational power. RGA-S and RGA-C are flexible enough to be used in any CNN network; Zhang et al. propose using them jointly in sequence to better capture both spatial and cross-channel relationships.

PaperSource

In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.

From the lookup's note on this name: Nothing resolved to this name, but 1 entry in Syntology's graph carry it; the most cited is “Ranking-Guided Alignment (RGA)”, a method in the paper “RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems” (arXiv:2602.12968, 0 citations). None of them is well cited, so for any better known sense of the name this is still a gap in coverage; they are listed so you can judge, not as a substitute. For arXiv:2602.12968: ask the lookup about it.

Near matches the lookup lists, each a different name: Ranking-Guided Alignment (RGA); Reward-Guided Autoregressive Graph Generation (RGA-Designer).

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: 11 · with a code link: 3 · 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 11 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 11 of 11, 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 23 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 Classification2
Autonomous Driving1
Blocking1
Clustering1
Combinatorial Optimization1
Continual Learning1
Domain Adaptation1
Drug Design1
Drug Discovery1
Image Segmentation1
Object Detection1
Person Re-Identification1
Quantization1
Relation1
Scene Segmentation1
Segmentation1
Semantic Segmentation1
Structural Health Monitoring1
Time Series1
Time Series Prediction1

Usage over time archive 2025-07-28

Papers per year tagged with RGA: 2019 to 2025, peak 3 3 0 2019: 1 paper 2019 2020: 3 papers 2020 2021: 1 paper 2021 2022: 1 paper 2022 2023: 1 paper 2023 2024: 1 paper 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (11 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