Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention

TL;DR

GLAMOR is a unified vehicle re-identification model that combines global and local attention mechanisms, achieving state-of-the-art accuracy, efficiency, and robustness across multiple datasets and challenging conditions.

Contribution

The paper introduces GLAMOR, a novel model with integrated global and local attention modules, improved backbone, and normalization techniques, outperforming existing methods in vehicle re-id.

Findings

Achieves high mAP scores on VeRi-776, VRIC, and VeRi-Wild datasets.

Model is 10x smaller and 25% faster than comparable approaches.

Outperforms recent methods in accuracy and efficiency.

Abstract

Vehicle re-identification (re-id) is a fundamental problem for modern surveillance camera networks. Existing approaches for vehicle re-id utilize global features and local features for re-id by combining multiple subnetworks and losses. In this paper, we propose GLAMOR, or Global and Local Attention MOdules for Re-id. GLAMOR performs global and local feature extraction simultaneously in a unified model to achieve state-of-the-art performance in vehicle re-id across a variety of adversarial conditions and datasets (mAPs 80.34, 76.48, 77.15 on VeRi-776, VRIC, and VeRi-Wild, respectively). GLAMOR introduces several contributions: a better backbone construction method that outperforms recent approaches, group and layer normalization to address conflicting loss targets for re-id, a novel global attention module for global feature extraction, and a novel local attention module for self-guided part-based local feature extraction that does not require supervision. Additionally, GLAMOR is a compact and fast model that is 10x smaller while delivering 25% better performance.