Learning deep part-aware embedding for person retrieval

Highlights：

• An improved triplet loss is introduced such that the global feature representations from the same identity are closely clustered for person ReID.

• A localization branch is proposed to automatically localize the discriminative person-wise parts or regions, only using identity labels in a weakly supervised manner.

• Via the learning simultaneously guided by the global branch and the localization branch, the proposed method can further improve the performance for ReID.

• The experimental results on four public available ReID datasets demonstrate the effectiveness and superiority of the proposed method.