Diff attention: A novel attention scheme for person re-identification

Abstract

The Person Re-ID has made great progress benefiting from the advance of deep neural networks and the attention mechanism in recent years. However, existing models and attentions for person Re-ID only focus on learning the robust features while neglecting the difference between features of pairs, which is the core of feature similarity matching tasks. To address this problem, we propose the Diff Attention idea and design Diff Attention Module to guide the network to learn a more discriminative attention map based on the difference of feature vectors. Taking the Diff Attention Module, we develop Diff Attention Framework to match various backbone Re-ID models and train them. To efficiently train Diff Attention Framework, we also propose two training strategies: Joint Training and Separate Training. Our framework and strategies have achieved excellent performance on Market-1501, CUHK03, and MSMT17 datasets. Our code will be made publicly available at https://github.com/linxin98/ReID-DiffAttention.