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

TL;DR

This paper introduces a novel framework for occluded person re-identification that leverages high-order relation and topology learning through graph convolutional layers, significantly improving matching accuracy.

Contribution

It proposes adaptive direction graph convolutional and cross-graph embedded-alignment layers to enhance feature discrimination and robust alignment in occluded ReID.

Findings

Outperforms state-of-the-art by 6.5% mAP on Occluded-Duke dataset

Effectively suppresses meaningless features during relation passing

Achieves robust alignment with graph matching and soft one-to-one matching

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.