Attention-Aware Compositional Network for Person Re-identification

TL;DR

This paper introduces the Attention-Aware Compositional Network (AACN), a novel framework that effectively utilizes pose estimation for improved person re-identification by handling pose variations, background clutter, and occlusions, achieving state-of-the-art results.

Contribution

The paper proposes a new AACN framework with pose-guided attention modules that better exploit pose information for person ReID, surpassing previous methods.

Findings

Achieves state-of-the-art performance on multiple datasets

Effectively handles pose variations and occlusions

Improves background suppression in feature extraction

Abstract

Person re-identification (ReID) is to identify pedestrians observed from different camera views based on visual appearance. It is a challenging task due to large pose variations, complex background clutters and severe occlusions. Recently, human pose estimation by predicting joint locations was largely improved in accuracy. It is reasonable to use pose estimation results for handling pose variations and background clutters, and such attempts have obtained great improvement in ReID performance. However, we argue that the pose information was not well utilized and hasn't yet been fully exploited for person ReID. In this work, we introduce a novel framework called Attention-Aware Compositional Network (AACN) for person ReID. AACN consists of two main components: Pose-guided Part Attention (PPA) and Attention-aware Feature Composition (AFC). PPA is learned and applied to mask out undesirable background features in pedestrian feature maps. Furthermore, pose-guided visibility scores are estimated for body parts to deal with part occlusion in the proposed AFC module. Extensive experiments with ablation analysis show the effectiveness of our method, and state-of-the-art results are achieved on several public datasets, including Market-1501, CUHK03, CUHK01, SenseReID, CUHK03-NP and DukeMTMC-reID.