Viet-Anh on Software Logo

What is: Relation-aware Global Attention?

SourceRelation-Aware Global Attention for Person Re-identification
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

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 XX to C×(H×W)C\times (H\times W) and the pairwise relation matrix RR(H×W)×(H×W)R \in \mathbb{R}^{(H\times W)\times (H\times W)} is computed using \begin{align} Q &= \delta(W^QX) \end{align} \begin{align} K &= \delta(W^KX) \end{align} \begin{align} R &= Q^TK \end{align} The relation vector rir_i at position ii is defined by stacking pairwise relations at all positions: \begin{align} r_i = [R(i, :); R(:,i)]
\end{align} and the spatial relation-aware feature yiy_i can be written as \begin{align} Y_i = [g^c_\text{avg}(\delta(W^\varphi x_i)); \delta(W^\phi r_i)] \end{align} where gavgcg^c_\text{avg} denotes global average pooling in the channel domain. Finally, the spatial attention score at position ii is given by \begin{align} a_i = \sigma(W_2\delta(W_1y_i)) \end{align} RGA-C has the same form as RGA-S, except for taking the input feature map as a set of H×WH\times 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.