Get started
Work

Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification

Year: 2016
Type: conference-paper
Abstract: Learning generic and robust feature representations with data from multiple domains for the same problem is of great value, especially for the problems that have multiple datasets but none of them are large enough to provide abundant data variations. In this work, we present a pipeline for learning deep feature representations from multiple domains with Convolutional Neural Networks (CNNs). When training a CNN with data from all the domains, some neurons learn representations shared across several domains, while some others are effective only for a specific one. Based on this important observation, we propose a Domain Guided Dropout algorithm to improve the feature learning procedure. Experiments show the effectiveness of our pipeline and the proposed algorithm. Our methods on the person re-identification problem outperform stateof-the-art methods on multiple datasets by large margins.
DOI: 10.1109/cvpr.2016.140
Language: English
Open Access status: green
OpenAlex ID: W2342611082
FWCI: 61.37
Cites: 60
Cited by: 977
Related to: 10