Vehicle re-identification is a challenging task that matches vehicle images captured by different cameras. Recent vehicle re-identification approaches exploit complex deep networks to learn viewpoint robust features for obtaining accurate re-identification results, which causes large computations in their testing phases to restrict the vehicle re-identification speed. In this paper, we propose a viewpoint robust knowledge distillation (VRKD) method for accelerating vehicle re-identification. The VRKD method consists of a complex teacher network and a simple student network. Specifically, the teacher network uses quadruple directional deep networks to learn viewpoint robust features. The student network only contains a shallow backbone sub-network and a global average pooling layer. The student network distills viewpoint robust knowledge from the teacher network via minimizing the Kullback-Leibler divergence between the posterior probability distributions resulted from the student and teacher networks. As a result, the vehicle re-identification speed is significantly accelerated since only the student network of small testing computations is demanded. Experiments on VeRi776 and VehicleID datasets show that the proposed VRKD method outperforms many state-of-the-art vehicle re-identification approaches with better accurate and speed performance.

车辆重新识别是一项具有挑战性的任务，需要匹配不同摄像头捕获的车辆图像。最近的车辆重新识别方法利用复杂的深度网络来学习观点鲁棒特征以获得准确的重新识别结果，这导致在其测试阶段进行大量计算以限制车辆重新识别速度。在本文中，我们提出了一种用于加速车辆重新识别的视点鲁棒知识蒸馏（VRKD）方法。VRKD 方法由复杂的教师网络和简单的学生网络组成。具体来说，教师网络使用四重定向深度网络来学习视点稳健特征。学生网络仅包含一个浅层主干子网络和一个全局平均池化层。学生网络通过最小化学生网络和教师网络产生的后验概率分布之间的 Kullback-Leibler 散度，从教师网络中提取观点稳健知识。结果，车辆重新识别速度显着加快，因为只需要小测试计算的学生网络。在 VeRi776 和 VehicleID 数据集上的实验表明，所提出的 VRKD 方法优于许多最先进的车辆重新识别方法，具有更好的准确度和速度性能。由于只需要小型测试计算的学生网络，因此车辆重新识别速度显着加快。在 VeRi776 和 VehicleID 数据集上的实验表明，所提出的 VRKD 方法优于许多最先进的车辆重新识别方法，具有更好的准确度和速度性能。由于只需要小型测试计算的学生网络，因此车辆重新识别速度显着加快。在 VeRi776 和 VehicleID 数据集上的实验表明，所提出的 VRKD 方法优于许多最先进的车辆重新识别方法，具有更好的准确度和速度性能。