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

arXiv: https://arxiv.org/abs/2011.14417 · HTML: https://mlsanity.com/paper/2011.14417/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2020.

## Built on by (most cited first, 4 of 4)

- [GiT: Graph Interactive Transformer for Vehicle Re-identification](https://mlsanity.com/paper/2107.05475/) (2021)
- [HSGNet: Object Re-identification with Hierarchical Similarity Graph Network](https://mlsanity.com/paper/2211.05486/) (2022)
- [DSAM-GN:Graph Network based on Dynamic Similarity Adjacency Matrices for Vehicle Re-identification](https://mlsanity.com/paper/2310.16694/) (2023)
- [SiamReID: Confuser Aware Siamese Tracker with Re-identification Feature](https://mlsanity.com/paper/2104.03510/) (2021)

## Abstract (arXiv)

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.