Cross-Correlated Attention Networks for Person Re-Identification

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.

Accepted by Image and Vision Computing

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Person Re-identification: Past, Present and Future
• Random Erasing Data Augmentation
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
• Pose Invariant Embedding for Deep Person Re-identification