Learning to Disentangle Scenes for Person Re-identification

Abstract

There are many challenging problems in the person re-identification (ReID) task, such as the occlusion and scale variation. Existing works usually tried to solve them by employing a one-branch network. This one-branch network needs to be robust to various challenging problems, which makes this network overburdened. This paper proposes to divide-and-conquer the ReID task. For this purpose, we employ several self-supervision operations to simulate different challenging problems and handle each challenging problem using different networks. Concretely, we use the random erasing operation and propose a novel random scaling operation to generate new images with controllable characteristics. A general multi-branch network, including one master branch and two servant branches, is introduced to handle different scenes. These branches learn collaboratively and achieve different perceptive abilities. In this way, the complex scenes in the ReID task are effectively disentangled, and the burden of each branch is relieved. The results from extensive experiments demonstrate that the proposed method achieves state-of-the-art performances on three ReID benchmarks and two occluded ReID benchmarks. Ablation study also shows that the proposed scheme and operations significantly improve the performance in various scenes. The code is available at https://git.openi.org.cn/zangxh/LDS.git.

Preprint Version; Accepted by Image and Vision Computing

References in corpus (11)

• Distilling the Knowledge in a Neural Network
• Person Re-identification: Past, Present and Future
• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
• Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
• Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
• Deep Hyperspherical Learning
• A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
• Interaction-and-Aggregation Network for Person Re-identification
• Variational Information Distillation for Knowledge Transfer
• View Confusion Feature Learning for Person Re-identification
• Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-Identification

Cited by in corpus (4)

• Body Part-Based Representation Learning for Occluded Person Re-Identification
• Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval
• A review of Recent Techniques for Person Re-Identification
• CLIP-ReIdent: Contrastive Training for Player Re-Identification