Unsupervised Domain Adaptive Re-Identification: Theory and Practice

Abstract

We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation. We first extend existing unsupervised domain adaptive classification theories to re-ID tasks. Concretely, we introduce some assumptions on the extracted feature space and then derive several loss functions guided by these assumptions. To optimize them, a novel self-training scheme for unsupervised domain adaptive re-ID tasks is proposed. It iteratively makes guesses for unlabeled target data based on an encoder and trains the encoder based on the guessed labels. Extensive experiments on unsupervised domain adaptive person re-ID and vehicle re-ID tasks with comparisons to the state-of-the-arts confirm the effectiveness of the proposed theories and self-training framework. Our code is available at \url{https://github.com/LcDog/DomainAdaptiveReID}.

References in corpus (1)

• Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking

Cited by in corpus (11)

• Domain Adaptive Person Re-Identification via Coupling Optimization
• Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification
• Exploring the Quality of GAN Generated Images for Person Re-Identification
• Style Normalization and Restitution for Generalizable Person Re-identification
• Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
• Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions
• Group-aware Label Transfer for Domain Adaptive Person Re-identification
• Unsupervised Few-shot Learning via Self-supervised Training
• Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
• Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID
• PGGANet: Pose Guided Graph Attention Network for Person Re-identification