Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions
arXiv:2109.06057
Abstract
Person re-identification (Re-ID) has been a significant research topic in the past decade due to its real-world applications and research significance. While supervised person Re-ID methods achieve superior performance over unsupervised counterparts, they can not scale to large unlabelled datasets and new domains due to the prohibitive labelling cost. Therefore, unsupervised person Re-ID has drawn increasing attention for its potential to address the scalability issue in person Re-ID. Unsupervised person Re-ID is challenging primarily due to lacking identity labels to supervise person feature learning. The corresponding solutions are diverse and complex, with various merits and limitations. Therefore, comprehensive surveys on this topic are essential to summarise challenges and solutions to foster future research. Existing person Re-ID surveys have focused on supervised methods from classifications and applications but lack detailed discussion on how the person Re-ID solutions address the underlying challenges. This survey review recent works on unsupervised person Re-ID from the perspective of challenges and solutions. Specifically, we provide an in-depth analysis of highly influential methods considering the four significant challenges in unsupervised person Re-ID: 1) lacking ground-truth identity labels to supervise person feature learning; 2) learning discriminative person features with pseudo-supervision; 3) learning cross-camera invariant person feature, and 4) the domain shift between datasets. We summarise and analyse evaluation results and provide insights on the effectiveness of the solutions. Finally, we discuss open issues and suggest some promising future research directions.
arXiv comment20 pages
References in corpus (27)
- Transformers in Vision: A Survey
- In Defense of the Triplet Loss for Person Re-Identification
- MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
- Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
- Harmonious Attention Network for Person Re-Identification
- Deeper and Wider Siamese Networks for Real-Time Visual Tracking
- Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
- Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
- Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification
- Unsupervised Domain Adaptive Re-Identification: Theory and Practice
- Person Search with Natural Language Description
- Unsupervised Person Re-identification by Soft Multilabel Learning
- Deformable Part Models are Convolutional Neural Networks
- Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification
- High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
- Dynamic Label Graph Matching for Unsupervised Video Re-Identification
- AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification
- Survey on Deep Learning Techniques for Person Re-Identification Task
- Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation
- Deep Association Learning for Unsupervised Video Person Re-identification
- Pose-guided Visible Part Matching for Occluded Person ReID
- Unsupervised Person Re-identification via Softened Similarity Learning
- Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification
- A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
- Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
- Intra-Inter Camera Similarity for Unsupervised Person Re-Identification
- Unity Style Transfer for Person Re-Identification