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

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

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.

LABNet：具有类平衡损失的本地图聚合网络，用于车辆重新识别

车辆重新识别是一项重要的计算机视觉任务，其目的是在各种视角看到的一组车辆中识别特定的车辆。基于深度学习的最新方法在主干特征提取器之后利用全局平均池化层，但是，这忽略了特征图上的任何空间推理。.. 在本文中，我们提出在骨干特征图上进行局部图聚合，以学习局部信息的关联，从而改善特征学习，并减少部分遮挡和背景混乱的影响。我们的局部图聚合网络将要素图的空间区域视为节点，并构建一个局部邻域图，该图在全局平均池化层之前执行局部特征聚合。我们进一步利用批处理规范化层来提高系统效率。此外，我们引入了类别平衡损失来补偿在最广泛使用的车辆重新识别数据集中发现的样本分布中的不平衡。最后，我们在三个流行的基准测试中评估了我们的方法，并表明我们的方法优于许多最新方法。 （阅读更多）