Relation-Aware Global Attention for Person Re-identification

Understand

For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matches well the key of re-id, i.e., discriminative feature learning.

• Previous approaches typically learn attention using local convolutions, ignoring the mining of knowledge from global structure patterns.
• Intuitively, the affinities among spatial positions/nodes in the feature map provide clustering-like information and are helpful for inferring semantics and thus attention, especially for person images where the feasible human poses are constrained.
• In this work, we propose an effective Relation-Aware Global Attention (RGA) module which captures the global structural information for better attention learning.