Learning to Adapt Invariance in Memory for Person Re-identification

Abstract

This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain. Existing methods are primary to reduce the inter-domain shift between the domains, which however usually overlook the relations among target samples. This paper investigates into the intra-domain variations of the target domain and proposes a novel adaptation framework w.r.t. three types of underlying invariance, i.e., Exemplar-Invariance, Camera-Invariance, and Neighborhood-Invariance. Specifically, an exemplar memory is introduced to store features of samples, which can effectively and efficiently enforce the invariance constraints over the global dataset. We further present the Graph-based Positive Prediction (GPP) method to explore reliable neighbors for the target domain, which is built upon the memory and is trained on the source samples. Experiments demonstrate that 1) the three invariance properties are indispensable for effective domain adaptation, 2) the memory plays a key role in implementing invariance learning and improves the performance with limited extra computation cost, 3) GPP could facilitate the invariance learning and thus significantly improves the results, and 4) our approach produces new state-of-the-art adaptation accuracy on three re-ID large-scale benchmarks.

arXiv commentExtension of conference version: arXiv:1904.01990

References in corpus (12)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Inductive Representation Learning on Large Graphs
• In Defense of the Triplet Loss for Person Re-Identification
• Learning Transferable Features with Deep Adaptation Networks
• Deep Convolutional Networks on Graph-Structured Data
• Person Re-identification: Past, Present and Future
• Random Erasing Data Augmentation
• Domain Separation Networks
• A Kernel Method for the Two-Sample Problem
• Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding
• Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
• Leveraging Virtual and Real Person for Unsupervised Person Re-identification

Cited by in corpus (7)

• Domain Adaptive Person Re-Identification via Coupling Optimization
• Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
• Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
• Unsupervised Multi-Source Domain Adaptation for Person Re-Identification
• Towards Discriminative Representation Learning for Unsupervised Person Re-identification
• Weakly supervised discriminative feature learning with state information for person identification
• Towards Precise Intra-camera Supervised Person Re-identification