论文标题
DSAM：高性能车辆重新识别的距离缩小的距离
DSAM: A Distance Shrinking with Angular Marginalizing Loss for High Performance Vehicle Re-identificatio
论文作者
论文摘要
车辆重新识别（REID）在计算机视觉中是一个重要但充满挑战的问题。与其他视觉物体（如面孔和人员）相比，车辆同时表现出更大的类内视点变化和类间的视觉相似性，从而使最不适合车辆REID的人设计的大多数退出损失功能。为了获得高性能的车辆REID模型，我们提出了一种新的距离，并使用角度边缘化（DSAM）损耗函数缩小，以使用本地验证和全局识别信息在原始特征空间（OFS）和特征角空间（FAS）中执行混合学习。具体而言，它缩小了原始特征空间中同一类的样本之间的距离，同时将不同类的样品保持在特征角度空间中。在训练过程的每次迭代中，都进行了收缩和边缘化操作，并且适用于不同的基于软马克斯的损失功能。我们在三个大型车辆REID数据集上评估了DSAM损耗函数，并与许多竞争性车辆REID方法进行了详细的分析和广泛的比较。实验结果表明，我们的DSAM损失在PKU-VD1-LARGE数据集上增加了SoftMax的损失：MAP的10.41％，CMC1为5.29％，CMC5为4.60％。此外，PKU-VehicleID数据集的地图增加了9.34％，Veri-776数据集增加了6.13％。源代码将被发布，以促进在此研究方向上进一步研究。
Vehicle Re-identification (ReID) is an important yet challenging problem in computer vision. Compared to other visual objects like faces and persons, vehicles simultaneously exhibit much larger intraclass viewpoint variations and interclass visual similarities, making most exiting loss functions designed for face recognition and person ReID unsuitable for vehicle ReID. To obtain a high-performance vehicle ReID model, we present a novel Distance Shrinking with Angular Marginalizing (DSAM) loss function to perform hybrid learning in both the Original Feature Space (OFS) and the Feature Angular Space (FAS) using the local verification and the global identification information. Specifically, it shrinks the distance between samples of the same class locally in the Original Feature Space while keeps samples of different classes far away in the Feature Angular Space. The shrinking and marginalizing operations are performed during each iteration of the training process and are suitable for different SoftMax based loss functions. We evaluate the DSAM loss function on three large vehicle ReID datasets with detailed analyses and extensive comparisons with many competing vehicle ReID methods. Experimental results show that our DSAM loss enhances the SoftMax loss by a large margin on the PKU-VD1-Large dataset: 10.41% for mAP, 5.29% for cmc1, and 4.60% for cmc5. Moreover, the mAP is increased by 9.34% on the PKU-VehicleID dataset and 6.13% on the VeRi-776 dataset. Source code will be released to facilitate further studies in this research direction.
