Methods › General › Attention Mechanisms › RGA
Relation-aware Global Attention
RGA
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.
Papers archive 2025-07-28
11 shown of 11, 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.
-
A Family of Robust Generalized Adaptive Filters and Application for Time-series Prediction 31 May 2025 · 0 repositories · arXiv:2506.00397
-
Bridging the Reality Gap in Digital Twins with Context-Aware, Physics-Guided Deep Learning 17 May 2025 · 0 repositories · arXiv:2505.11847
-
CogniSNN: A First Exploration to Random Graph Architecture based Spiking Neural Networks with Enhanced Expandability and Neuroplasticity 9 May 2025 · 0 repositories · arXiv:2505.05992
-
Region-Guided Attack on the Segment Anything Model (SAM) 5 Nov 2024 · 0 repositories · arXiv:2411.02974
-
Rate Gradient Approximation Attack Threats Deep Spiking Neural Networks 1 Jan 2023 · 1 repository
-
Reinforced Genetic Algorithm for Structure-based Drug Design 28 Nov 2022 · 1 repository · arXiv:2211.16508
-
On Use of the Moore-Penrose Pseudoinverse for Evaluating the RGA of Non-Square Systems 17 Jun 2021 · 0 repositories · arXiv:2106.09766
-
Adversarial Blocking Bandits 1 Dec 2020 · 0 repositories
-
Quantization in Relative Gradient Angle Domain For Building Polygon Estimation 10 Jul 2020 · 0 repositories · arXiv:2007.05617
-
Delving into the Imbalance of Positive Proposals in Two-stage Object Detection 23 May 2020 · 0 repositories · arXiv:2005.11472
-
Relation-Aware Global Attention for Person Re-identification 5 Apr 2019 · 1 repository · arXiv:1904.02998Syntology ran 0 of 6 samples · 6 unverified
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.
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