Body Part-Based Representation Learning for Occluded Person Re-Identification

Occluded person re-identification (ReID) is a person retrieval task which aims at matching occluded person images with holistic ones. For addressing occluded ReID, partbased methods have been shown beneficial as they offer fine-grained information and are well suited to represent partially visible human bodies. However, training a part-based model is a challenging task for two reasons. Firstly, individual body part appearance is not as discriminative as global appearance (two distinct IDs might have the same local appearance), this means standard ReID training objectives using identity labels are not adapted to local feature learning. Secondly, ReID datasets are not provided with human topographical annotations. In this work, we propose BPBreID, a body part-based ReID model for solving the above issues. We first design two modules for predicting body part attention maps and producing body partbased features of the ReID target. We then propose GiLt, a novel training scheme for learning part-based representations that is robust to occlusions and non-discriminative local appearance. Extensive experiments on popular holistic and occluded datasets show the effectiveness of our proposed method, which outperforms state-of-the-art methods by 0:7% mAP and 5:6% rank-1 accuracy on the challenging Occluded-Duke dataset. Our code is available at https://github.com/VlSomers/bpbreid.

Automated summary

In this work, we propose BPBreID, a body part-based ReID model for solving the challenges of occlusions and non-discriminative local appearance. Our method designs two modules to predict body part attention maps and generate part-based features, and introduces GiLt training scheme for robust part-based representation learning. Extensive experiments show the effectiveness of our proposed method, achieving 0.7% mAP improvement and 5.6% rank-1 accuracy improvement on the challenging Occluded-Duke dataset.