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

By Guan'an Wang, Shuo Yang, Huanyu Liu, Zhicheng Wang, Yang Yang, Shuliang Wang, Gang Yu, Erjin Zhou. Computer Vision and Pattern Recognition, 2020

475 citations recorded by the source corpus.

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 to learn feature maps and key-points estimation model to extract semantic local features. Even so, occluded images still suffer from occlusion and outliers. Then, we view the extracted 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 direction and degree of linkage. When aligning two groups of local features, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to joint learn and embed topology information to local features, and straightly predict similarity score. The proposed CGEA layer can both take full use of alignment learned by graph matching and replace sensitive one-to-one alignment 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 by $6.5\%$ mAP scores on Occluded-Duke dataset.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5fffb5d73616b3f9ae698470feb2f516fd561dd0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Feng Wu
2. Yongdong Zhang
3. Chunhua Shen
4. Xinlong Wang
5. Tianzhu Zhang
6. Yulin Li
7. Xiang Liu
8. Jianfeng He

In Computer Vision and Pattern Recognition

1. Xinlong Wang
2. Yongdong Zhang
3. Chunhua Shen
4. Feng Wu
5. Tianzhu Zhang
6. Jiawang Bian
7. Siyuan Li
8. Mingyu You

Citations in the corpus

• Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, methodology): “Compared with PVPM and HOReID, which are SOTA occluded ReID methods with key-points information, our method achieves much better performance, surpassing them by at least +9 .”
• Diverse Knowledge Distillation for End-to-End Person Search (2020, methodology): “Recent work (Wang et al. 2020a) consider the consistency requirements between detection and Re-ID, and propose an identity-guided query detector and a detection adapted reID model.”
• CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels (2022, background): “HOReID (Wang et al. 2020) extends the traditional attention into high-order computation, giving more discriminative features.”