Domain Adaptive Attention Model for Unsupervised Cross-Domain Person Re-Identification

05/25/2019
by   Yangru Huang, et al.
0

Person re-identification (Re-ID) across multiple datasets is a challenging yet important task due to the possibly large distinctions between different datasets and the lack of training samples in practical applications. This work proposes a novel unsupervised domain adaption framework which transfers discriminative representations from the labeled source domain (dataset) to the unlabeled target domain (dataset). We propose to formulate the domain adaption task as an one-class classification problem with a novel domain similarity loss. Given the feature map of any image from a backbone network, a novel domain adaptive attention model (DAAM) first automatically learns to separate the feature map of an image to a domain-shared feature (DSH) map and a domain-specific feature (DSP) map simultaneously. Specially, the residual attention mechanism is designed to model DSP feature map for avoiding negative transfer. Then, a DSH branch and a DSP branch are introduced to learn DSH and DSP feature maps respectively. To reduce domain divergence caused by that the source and target datasets are collected from different environments, we force to project the DSH feature maps from different domains to a new nominal domain, and a novel domain similarity loss is proposed based on one-class classification. In addition, a novel unsupervised person Re-ID loss is proposed to take full use of unlabeled target data. Extensive experiments on the Market-1501 and DukeMTMC-reID benchmarks demonstrate state-of-the-art performance of the proposed method. Code will be released to facilitate further studies on the cross-domain person re-identification task.

READ FULL TEXT

page 4

page 8

research
03/25/2021

Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification

Unsupervised domain adaptive (UDA) person re-identification (ReID) aims ...
research
09/20/2019

Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

Person re-identification (re-ID) aims at recognizing the same person fro...
research
05/30/2019

Attention: A Big Surprise for Cross-Domain Person Re-Identification

In this paper, we focus on model generalization and adaptation for cross...
research
07/09/2019

Adaptive Exploration for Unsupervised Person Re-Identification

Due to domain bias, directly deploying a deep person re-identification (...
research
11/06/2020

Domain Adaptive Person Re-Identification via Coupling Optimization

Domain adaptive person Re-Identification (ReID) is challenging owing to ...
research
12/19/2017

Hierarchical Cross Network for Person Re-identification

Person re-identification (person re-ID) aims at matching target person(s...
research
04/23/2019

Interpretable and Generalizable Deep Image Matching with Adaptive Convolutions

For image matching tasks, like face recognition and person re-identifica...

Please sign up or login with your details

Forgot password? Click here to reset