CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification

TL;DR

This paper introduces CA3Net, a novel deep learning model that combines attribute and appearance features with attention mechanisms and spatial dependencies to improve person re-identification accuracy across camera views.

Contribution

The paper presents a new network architecture that jointly learns attribute and appearance features using attention and LSTM modules for robust person re-identification.

Findings

Outperforms existing methods on Market-1501 and DukeMTMC-reID datasets.

Effectively exploits semantic attribute context and spatial dependencies.

Achieves higher re-identification accuracy with comprehensive pedestrian representations.

Abstract

Person re-identification aims to identify the same pedestrian across non-overlapping camera views. Deep learning techniques have been applied for person re-identification recently, towards learning representation of pedestrian appearance. This paper presents a novel Contextual-Attentional Attribute-Appearance Network (CA3Net) for person re-identification. The CA3Net simultaneously exploits the complementarity between semantic attributes and visual appearance, the semantic context among attributes, visual attention on attributes as well as spatial dependencies among body parts, leading to discriminative and robust pedestrian representation. Specifically, an attribute network within CA3Net is designed with an Attention-LSTM module. It concentrates the network on latent image regions related to each attribute as well as exploits the semantic context among attributes by a LSTM module. An appearance network is developed to learn appearance features from the full body, horizontal and vertical body parts of pedestrians with spatial dependencies among body parts. The CA3Net jointly learns the attribute and appearance features in a multi-task learning manner, generating comprehensive representation of pedestrians. Extensive experiments on two challenging benchmarks, i.e., Market-1501 and DukeMTMC-reID datasets, have demonstrated the effectiveness of the proposed approach.