Body Part-Based Representation Learning for Occluded Person Re-Identification
Preprint
Abstract
Occluded person re-identification (ReID) is a person retrieval task which aims at matching occluded person images with holistic ones. For addressing occluded ReID, part-based 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 part-based 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.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- AAformer: Auto-Aligned Transformer for Person Re-IdentificationIEEE Transactions on Neural Networks and Learning Systems, 2023
- Feature Erasing and Diffusion Network for Occluded Person Re-Identification2022
- MHSA-Net: Multihead Self-Attention Network for Occluded Person Re-IdentificationIEEE Transactions on Neural Networks and Learning Systems, 2022
- Learning to Know Where to See: A Visibility-Aware Approach for Occluded Person Re-identification2021
- Occluded Person Re-Identification with Single-scale Global Representations2021
- Occlude Them All: Occlusion-Aware Attention Network for Occluded Person Re-ID2021
- Deep Learning for Person Re-Identification: A Survey and OutlookIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Human Parsing Based Alignment With Multi-Task Learning For Occluded Person Re-Identification2020
- Pose-Invariant Embedding for Deep Person Re-IdentificationIEEE Transactions on Image Processing, 2019
- Part-Aligned Bilinear Representations for Person Re-identification2018