Unsupervised Multi-Source Domain Adaptation for Person Re-Identification

Abstract

Unsupervised domain adaptation (UDA) methods for person re-identification (re-ID) aim at transferring re-ID knowledge from labeled source data to unlabeled target data. Although achieving great success, most of them only use limited data from a single-source domain for model pre-training, making the rich labeled data insufficiently exploited. To make full use of the valuable labeled data, we introduce the multi-source concept into UDA person re-ID field, where multiple source datasets are used during training. However, because of domain gaps, simply combining different datasets only brings limited improvement. In this paper, we try to address this problem from two perspectives, \ie{} domain-specific view and domain-fusion view. Two constructive modules are proposed, and they are compatible with each other. First, a rectification domain-specific batch normalization (RDSBN) module is explored to simultaneously reduce domain-specific characteristics and increase the distinctiveness of person features. Second, a graph convolutional network (GCN) based multi-domain information fusion (MDIF) module is developed, which minimizes domain distances by fusing features of different domains. The proposed method outperforms state-of-the-art UDA person re-ID methods by a large margin, and even achieves comparable performance to the supervised approaches without any post-processing techniques.

CVPR 2021 Oral

References in corpus (10)

• In Defense of the Triplet Loss for Person Re-Identification
• Learning Transferable Features with Deep Adaptation Networks
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• Differentiable Learning-to-Normalize via Switchable Normalization
• Unsupervised Deep Learning by Neighbourhood Discovery
• Learning to Adapt Invariance in Memory for Person Re-identification
• Similarity-preserving Image-image Domain Adaptation for Person Re-identification