Online Auto-Aligned Transformer
AAformer: Auto-Aligned Transformer for Person Re-Identification
Person re-identification (re-id) is a challenging vision task in which there are inevitable misalignment issues caused by pose/viewpoints variations, etc.To address this problem, we develop a novel alignmentframework for person re-identification (re-id) through adding the learnable vectors of"part tokens"to learn the part representations and integrating the part alignment into the self-attention.The part tokens can be regarded as the part prototypes, and a fast variant of the sinkhorn-knopp algorithm is employed to cluster the patch embeddings to part tokens online.Extensive experiments validate the effectiveness of part tokens and the superiority of aaformer over various state-of-the-art cnn-based methods.
