Attribute-Guided Collaborative Learning for Partial Person Re-Identification

Authors

Haoyu Zhang, Harbin Institute of Technology
Meng Liu, Shandong Jianzhu University
Yuhong Li, Alibaba Group Holding Limited
Ming Yan, Alibaba Group Holding Limited
Zan Gao, Qilu University of Technology
Xiaojun Chang, University of Technology Sydney & Mohamed bin Zayed University of Artificial IntelligenceFollow
Liqiang Nie, Harbin Institute of Technology

Document Type

Article

Publication Title

IEEE Transactions on Pattern Analysis and Machine Intelligence

Abstract

Partial person re-identification (ReID) aims to solve the problem of image spatial misalignment due to occlusions or out-of-views. Despite significant progress through the introduction of additional information, such as human pose landmarks, mask maps, and spatial information, partial person ReID remains challenging due to noisy keypoints and impressionable pedestrian representations. To address these issues, we propose a unified attribute-guided collaborative learning scheme for partial person ReID. Specifically, we introduce an adaptive threshold-guided masked graph convolutional network that can dynamically remove untrustworthy edges to suppress the diffusion of noisy keypoints. Furthermore, we incorporate human attributes and devise a cyclic heterogeneous graph convolutional network to effectively fuse cross-modal pedestrian information through intra- and inter-graph interaction, resulting in robust pedestrian representations. Finally, to enhance keypoint representation learning, we design a novel part-based similarity constraint based on the axisymmetric characteristic of the human body. Extensive experiments on multiple public datasets have shown that our model achieves superior performance compared to other state-of-the-art baselines.

First Page

14144

Last Page

14160

DOI

10.1109/TPAMI.2023.3312302

Publication Date

12-1-2023

Keywords

Intra- and inter-graph interaction, masked graph convolution, partial person re-identification, Pedestrians, Feature extraction, Visualization, Noise measurement, Transformers, Semantics, Representation learning

Comments

IR Deposit conditions:

OA version (pathway a) Accepted version

No embargo

When accepted for publication, set statement to accompany deposit (see policy)

Must link to publisher version with DOI

Publisher copyright and source must be acknowledged

Recommended Citation

H. Zhang et al., "Attribute-Guided Collaborative Learning for Partial Person Re-Identification," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 12, pp. 14144-14160, Dec. 2023, doi: 10.1109/TPAMI.2023.3312302.

Additional Links

https://doi.org/10.1109/TPAMI.2023.3312302