Learning to Disentangle Scenes for Person Re-identification
arXiv:2111.05476 · doi:10.1016/j.imavis.2021.104330
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.
arXiv commentPreprint Version; Accepted by Image and Vision Computing
References in corpus (29)
- Adam: A Method for Stochastic Optimization
- Distilling the Knowledge in a Neural Network
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- In Defense of the Triplet Loss for Person Re-Identification
- Additive Margin Softmax for Face Verification
- Person Re-identification: Past, Present and Future
- NormFace: L2 Hypersphere Embedding for Face Verification
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
- Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
- Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
- Omni-Scale Feature Learning for Person Re-Identification
- Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
- Second-order Non-local Attention Networks for Person Re-identification
- Re-ranking Person Re-identification with k-reciprocal Encoding
- Learning a Discriminative Null Space for Person Re-identification
- ABD-Net: Attentive but Diverse Person Re-Identification
- Deep Hyperspherical Learning
- Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach
- A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
- High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
- Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
- Mixed High-Order Attention Network for Person Re-Identification
- Interaction-and-Aggregation Network for Person Re-identification
- Variational Information Distillation for Knowledge Transfer
- Pose-guided Visible Part Matching for Occluded Person ReID
- Knowledge Distillation for End-to-End Person Search
- View Confusion Feature Learning for Person Re-identification
- Occluded Person Re-identification
- Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-Identification