High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification

Abstract

Occluded person re-identification (ReID) aims to match occluded person images to holistic ones across dis-joint cameras. In this paper, we propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. At first, we use a CNN backbone and a key-points estimation model to extract semantic local features. Even so, occluded images still suffer from occlusion and outliers. Then, we view the local features of an image as nodes of a graph and propose an adaptive direction graph convolutional (ADGC)layer to pass relation information between nodes. The proposed ADGC layer can automatically suppress the message-passing of meaningless features by dynamically learning di-rection and degree of linkage. When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score. The proposed CGEA layer not only take full use of alignment learned by graph matching but also re-place sensitive one-to-one matching with a robust soft one. Finally, extensive experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed method. Specifically, our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.

arXiv commentaccepted by CVPR'20

References in corpus (12)

• Semi-Supervised Classification with Graph Convolutional Networks
• In Defense of the Triplet Loss for Person Re-Identification
• Person Re-identification: Past, Present and Future
• Random Erasing Data Augmentation
• FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
• Recognizing Partial Biometric Patterns
• MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification
• Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach
• A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
• Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification
• STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification

Cited by in corpus (6)

• MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification
• Incomplete Descriptor Mining with Elastic Loss for Person Re-Identification
• Learning to Disentangle Scenes for Person Re-identification
• Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions
• Faster Person Re-Identification
• Progressive Multi-stage Feature Mix for Person Re-Identification