Cross-Correlated Attention Networks for Person Re-Identification

Date

2020

Authors

Zhou, Jieming
Roy, Soumava Kumar
Fang, Pengfei
Harandi, Mehrtash
Petersson, Lars

Journal Title

Journal ISSN

Volume Title

Publisher

Elsevier

Abstract

Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations to name a few when the task of person re-identification is considered. Attention mechanisms have recently proven to be successful in handling the aforementioned challenges to some degree. However previous designs fail to capture inherent inter-dependencies between the attended features; leading to restricted interactions between the attention blocks. In this paper, we propose a new attention module called Cross-Correlated Attention (CCA); which aims to overcome such limitations by maximizing the information gain between different attended regions. Moreover, we also propose a novel deep network that makes use of different attention mechanisms to learn robust and discriminative representations of person images. The resulting model is called the Cross-Correlated Attention Network (CCAN). Extensive experiments demonstrate that the CCAN comfortably outperforms current state-of-the-art algorithms by a tangible margin. Modeling the inherent spatial relations between different attended regions within the deep architecture. Joint end-to-end cross correlated attention and representational learning. State-of-the-art results in terms of mAP and Rank-1 accuracies across several challenging datasets.

Description

Keywords

Attention, Feature extraction, Cross correlation, Person Re-Identification, Surveillance

Citation

Source

Image and Vision Computing

Type

Journal article

Book Title

Entity type

Access Statement

License Rights

DOI

10.1016/j.imavis.2020.103931

Restricted until

2099-12-31