论文标题
通过基于摄像机的批准化重新考虑人员重新识别的分布差距
Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization
论文作者
论文摘要
重新识别（REID）的基本困难在于学习单个相机之间的对应关系。它强烈要求昂贵的摄像机间注释，但是训练有素的模型不能很好地转移到以前看不见的摄像机上。这些问题大大限制了REID的应用。本文重新考虑了常规REID方法的工作机制，并提出了新的解决方案。借助有效的运算符，我们将基于相机的批处理标准化（CBN）迫使所有相机的图像数据落在相同的子空间上，因此任何相机对之间的分布差距在很大程度上缩小了。这种一致性带来了两个好处。首先，受过训练的模型具有更好的能力，可以通过看不见的相机以及在多个训练集中进行转移。其次，我们可以依靠相机内注释，这些注释因缺乏跨相机信息而被低估了，以实现竞争性的REID性能。在各种REID任务上进行的实验证明了我们方法的有效性。该代码可在https://github.com/automan000/camera-later-person-reid上找到。
The fundamental difficulty in person re-identification (ReID) lies in learning the correspondence among individual cameras. It strongly demands costly inter-camera annotations, yet the trained models are not guaranteed to transfer well to previously unseen cameras. These problems significantly limit the application of ReID. This paper rethinks the working mechanism of conventional ReID approaches and puts forward a new solution. With an effective operator named Camera-based Batch Normalization (CBN), we force the image data of all cameras to fall onto the same subspace, so that the distribution gap between any camera pair is largely shrunk. This alignment brings two benefits. First, the trained model enjoys better abilities to generalize across scenarios with unseen cameras as well as transfer across multiple training sets. Second, we can rely on intra-camera annotations, which have been undervalued before due to the lack of cross-camera information, to achieve competitive ReID performance. Experiments on a wide range of ReID tasks demonstrate the effectiveness of our approach. The code is available at https://github.com/automan000/Camera-based-Person-ReID.
