LABNet: Local Graph Aggregation Network with Class Balanced Loss for Vehicle Re-Identification

TL;DR

This paper introduces LABNet, a vehicle re-identification method that employs local graph aggregation on feature maps and a class balanced loss, significantly improving accuracy by addressing spatial reasoning and data imbalance.

Contribution

The paper proposes a novel local graph aggregation network with class balanced loss for vehicle re-identification, enhancing feature learning and handling dataset imbalance.

Findings

Outperforms state-of-the-art methods on three benchmarks.

Effectively reduces effects of occlusion and background clutter.

Improves feature representation through local graph aggregation.

Abstract

Vehicle re-identification is an important computer vision task where the objective is to identify a specific vehicle among a set of vehicles seen at various viewpoints. Recent methods based on deep learning utilize a global average pooling layer after the backbone feature extractor, however, this ignores any spatial reasoning on the feature map. In this paper, we propose local graph aggregation on the backbone feature map, to learn associations of local information and hence improve feature learning as well as reduce the effects of partial occlusion and background clutter. Our local graph aggregation network considers spatial regions of the feature map as nodes and builds a local neighborhood graph that performs local feature aggregation before the global average pooling layer. We further utilize a batch normalization layer to improve the system effectiveness. Additionally, we introduce a class balanced loss to compensate for the imbalance in the sample distributions found in the most widely used vehicle re-identification datasets. Finally, we evaluate our method in three popular benchmarks and show that our approach outperforms many state-of-the-art methods.