Unsupervised Person Re-identification via Multi-label Classification

Abstract

The challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels. This paper formulates unsupervised person ReID as a multi-label classification task to progressively seek true labels. Our method starts by assigning each person image with a single-class label, then evolves to multi-label classification by leveraging the updated ReID model for label prediction. The label prediction comprises similarity computation and cycle consistency to ensure the quality of predicted labels. To boost the ReID model training efficiency in multi-label classification, we further propose the memory-based multi-label classification loss (MMCL). MMCL works with memory-based non-parametric classifier and integrates multi-label classification and single-label classification in a unified framework. Our label prediction and MMCL work iteratively and substantially boost the ReID performance. Experiments on several large-scale person ReID datasets demonstrate the superiority of our method in unsupervised person ReID. Our method also allows to use labeled person images in other domains. Under this transfer learning setting, our method also achieves state-of-the-art performance.

CVPR2020

Cited by in corpus (8)

• Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold
• Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id
• Unsupervised Person Re-identification with Stochastic Training Strategy
• Learning Invariance from Generated Variance for Unsupervised Person Re-identification
• Domain Adaptive Person Re-Identification via Coupling Optimization
• MHFC: Multi-Head Feature Collaboration for Few-Shot Learning
• Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning
• Camera-aware Style Separation and Contrastive Learning for Unsupervised Person Re-identification