Domain Adaptive Attention Learning for Unsupervised Person Re-Identification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Yangru, Peng, Peixi, Jin, Yi, Li, Yidong, Xing, Junliang, Ge, Shiming
Format: Preprint
Published: 2019
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909224169111552
author Huang, Yangru
Peng, Peixi
Jin, Yi
Li, Yidong
Xing, Junliang
Ge, Shiming
author_facet Huang, Yangru
Peng, Peixi
Jin, Yi
Li, Yidong
Xing, Junliang
Ge, Shiming
contents Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper proposes a domain adaptive attention learning approach to reliably transfer discriminative representation from the labeled source domain to the unlabeled target domain. In this approach, a domain adaptive attention model is learned to separate the feature map into domain-shared part and domain-specific part. In this manner, the domain-shared part is used to capture transferable cues that can compensate cross-dataset distinctions and give positive contributions to the target task, while the domain-specific part aims to model the noisy information to avoid the negative transfer caused by domain diversity. A soft label loss is further employed to take full use of unlabeled target data by estimating pseudo labels. Extensive experiments on the Market-1501, DukeMTMC-reID and MSMT17 benchmarks demonstrate the proposed approach outperforms the state-of-the-arts.
format Preprint
id arxiv_https___arxiv_org_abs_1905_10529
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
Huang, Yangru
Peng, Peixi
Jin, Yi
Li, Yidong
Xing, Junliang
Ge, Shiming
Computer Vision and Pattern Recognition
Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper proposes a domain adaptive attention learning approach to reliably transfer discriminative representation from the labeled source domain to the unlabeled target domain. In this approach, a domain adaptive attention model is learned to separate the feature map into domain-shared part and domain-specific part. In this manner, the domain-shared part is used to capture transferable cues that can compensate cross-dataset distinctions and give positive contributions to the target task, while the domain-specific part aims to model the noisy information to avoid the negative transfer caused by domain diversity. A soft label loss is further employed to take full use of unlabeled target data by estimating pseudo labels. Extensive experiments on the Market-1501, DukeMTMC-reID and MSMT17 benchmarks demonstrate the proposed approach outperforms the state-of-the-arts.
title Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/1905.10529