Cross-Correlated Attention Networks for Person Re-Identification

TL;DR

This paper introduces the Cross-Correlated Attention Network (CCAN), a novel deep learning model that enhances person re-identification by capturing inter-dependent features through a new attention mechanism, significantly outperforming existing methods.

Contribution

The paper proposes the Cross-Correlated Attention (CCA) module and integrates it into a new network architecture, improving feature interaction and robustness in person re-identification.

Findings

CCAN outperforms state-of-the-art algorithms on benchmark datasets.

The CCA module effectively captures inter-dependencies between attended regions.

Extensive experiments validate the superiority of the proposed approach.

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.