IEEE Trans Image Process. 2019 Mar;28(3):1176-1190. doi: 10.1109/TIP.2018.2874313. Epub 2018 Oct 8.
Person re-identification (re-ID) is a cross-camera retrieval task that suffers from image style variations caused by different cameras. The art implicitly addresses this problem by learning a camera-invariant descriptor subspace. In this paper, we explicitly consider this challenge by introducing camera style (CamStyle). CamStyle can serve as a data augmentation approach that reduces the risk of deep network overfitting and that smooths the CamStyle disparities. Specifically, with a style transfer model, labeled training images can be style transferred to each camera, and along with the original training samples, form the augmented training set. This method, while increasing data diversity against overfitting, also incurs a considerable level of noise. In the effort to alleviate the impact of noise, the label smooth regularization (LSR) is adopted. The vanilla version of our method (without LSR) performs reasonably well on few camera systems in which overfitting often occurs. With LSR, we demonstrate consistent improvement in all systems regardless of the extent of overfitting. We also report competitive accuracy compared with the state of the art on Market-1501 and DukeMTMC-re-ID. Importantly, CamStyle can be employed to the challenging problems of one view learning and unsupervised domain adaptation (UDA) in person re-identification (re-ID), both of which have critical research and application significance. The former only has labeled data in one camera view and the latter only has labeled data in the source domain. Experimental results show that CamStyle significantly improves the performance of the baseline in the two problems. Specially, for UDA, CamStyle achieves state-of-the-art accuracy based on a baseline deep re-ID model on Market-1501 and DukeMTMC-reID. Our code is available at: https://github.com/zhunzhong07/CamStyle .
人体重识别（re-ID）是一项跨摄像机检索任务，会受到不同摄像机造成的图像风格变化的影响。该领域的艺术方法通过学习相机不变描述符子空间来解决这个问题。在本文中，我们通过引入相机风格（CamStyle）来明确考虑这个挑战。CamStyle 可以作为一种数据增强方法，降低深度网络过拟合的风险，并平滑 CamStyle 差异。具体来说，使用样式传输模型，可以将标记的训练图像样式传输到每个相机，并与原始训练样本一起形成增强的训练集。这种方法在增加数据多样性以防止过拟合的同时，也会引入相当大的噪声。为了减轻噪声的影响，采用了标签平滑正则化（LSR）。我们的方法的香草版本（没有 LSR）在经常发生过拟合的少数摄像机系统中表现相当不错。使用 LSR，我们证明了在所有系统中都有一致的改进，无论过拟合的程度如何。我们还在 Market-1501 和 DukeMTMC-re-ID 上的最新技术水平上报告了有竞争力的准确性。重要的是，CamStyle 可以应用于人体重识别（re-ID）中的单视图学习和无监督领域自适应（UDA）这两个具有重要研究和应用意义的挑战性问题。前者只有一个摄像机视图的标记数据，后者只有源域的标记数据。实验结果表明，CamStyle 显著提高了基线在这两个问题中的性能。特别是对于 UDA，CamStyle 在 Market-1501 和 DukeMTMC-reID 上基于基线深度 re-ID 模型实现了最先进的准确性。我们的代码可在 https://github.com/zhunzhong07/CamStyle 获得。
