Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification

Abstract

Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. To handle this problem, some recent works adopt clustering algorithms to off-line generate pseudo labels, which can then be used as the supervision signal for on-line feature learning in the target domain. However, the off-line generated labels often contain lots of noise that significantly hinders the discriminability of the on-line learned features, and thus limits the final UDA re-ID performance. To this end, we propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID. Specifically, at the off-line phase, a new hierarchical clustering scheme is proposed, which selects representative prototypes for every coarse cluster. Thus, labels can be effectively refined by using the inherent hierarchical information of person images. Besides, at the on-line phase, we propose an instant memory spread-out (IM-spread-out) regularization, that takes advantage of the proposed instant memory bank to store sample features of the entire dataset and enable spread-out feature learning over the entire training data instantly. Our Dual-Refinement method reduces the influence of noisy labels and refines the learned features within the alternative training process. Experiments demonstrate that our method outperforms the state-of-the-art methods by a large margin.

arXiv comment14 pages, 5 figures

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• In Defense of the Triplet Loss for Person Re-Identification
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Learning Discriminative Features with Multiple Granularities for Person Re-Identification
• Person Re-identification: Past, Present and Future
• Random Erasing Data Augmentation
• A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
• Making Risk Minimization Tolerant to Label Noise
• Are Anchor Points Really Indispensable in Label-Noise Learning?
• Adaptive Exploration for Unsupervised Person Re-Identification
• Circle Loss: A Unified Perspective of Pair Similarity Optimization
• Face Clustering: Representation and Pairwise Constraints
• Unsupervised Deep Learning by Neighbourhood Discovery
• Receptive Multi-granularity Representation for Person Re-Identification

Cited by in corpus (3)

• Group-aware Label Transfer for Domain Adaptive Person Re-identification
• Generalizable Person Re-identification with Relevance-aware Mixture of Experts
• CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identification