Next Article in Journal
An Inverter Topology for Wireless Power Transfer System with Multiple Transmitter Coils
Next Article in Special Issue
A Trimmed Clustering-Based l1-Principal Component Analysis Model for Image Classification and Clustering Problems with Outliers
Previous Article in Journal
Analysis of a Supercapacitor/Battery Hybrid Power System for a Bulk Carrier
Previous Article in Special Issue
Adaptive Context-Aware and Structural Correlation Filter for Visual Tracking
Article Menu

Export Article

Open AccessArticle
Appl. Sci. 2019, 9(8), 1550;

Attention-Aware Adversarial Network for Person Re-Identification

School of Mathematical Sciences, Dalian University of Technology, Dalian 116024, China
Department of Basic Courses, Criminal Investigation Police University of China, Shenyang 110854, China
Author to whom correspondence should be addressed.
Received: 19 March 2019 / Revised: 4 April 2019 / Accepted: 9 April 2019 / Published: 14 April 2019
(This article belongs to the Special Issue Advanced Intelligent Imaging Technology)
PDF [1045 KB, uploaded 17 April 2019]


Person re-identification (re-ID) is a fundamental problem in the field of computer vision. The performance of deep learning-based person re-ID models suffers from a lack of training data. In this work, we introduce a novel image-specific data augmentation method on the feature map level to enforce feature diversity in the network. Furthermore, an attention assignment mechanism is proposed to enforce that the person re-ID classifier focuses on nearly all important regions of the input person image. To achieve this, a three-stage framework is proposed. First, a baseline classification network is trained for person re-ID. Second, an attention assignment network is proposed based on the baseline network, in which the attention module learns to suppress the response of the current detected regions and re-assign attentions to other important locations. By this means, multiple important regions for classification are highlighted by the attention map. Finally, the attention map is integrated in the attention-aware adversarial network (AAA-Net), which generates high-performance classification results with an adversarial training strategy. We evaluate the proposed method on two large-scale benchmark datasets, including Market1501 and DukeMTMC-reID. Experimental results show that our algorithm performs favorably against the state-of-the-art methods. View Full-Text
Keywords: person re-identification; attention mechanism; adversarial network person re-identification; attention mechanism; adversarial network

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Shen, A.; Wang, H.; Wang, J.; Tan, H.; Liu, X.; Cao, J. Attention-Aware Adversarial Network for Person Re-Identification. Appl. Sci. 2019, 9, 1550.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics



[Return to top]
Appl. Sci. EISSN 2076-3417 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top