SDL: Spectrum-Disentangled Representation Learning for Visible-Infrared Person Re-Identification
SDL: Spectrum-Disentangled Representation Learning for Visible-Infrared Person Re-Identification
复制标题
DOI：
10.1109/tcsvt.2019.2963721
复制
发表时间：
2020-01
影响因子：
8.4
通讯作者：
Kajal Kansal;A. Subramanyam;Z. Wang;S. Satoh
中科院分区：
文献类型：
--
作者：
Kajal Kansal;A. Subramanyam;Z. Wang;S. Satoh
可见-红外身份识别（RGB-IR ReID）对于弱光照条件下的监控应用非常重要。由于特征表示的差异不仅在于人的姿势、视点或光照变化，而且还来自于巨大的光谱差异，因此该任务在实践中变得非常具有挑战性。现有的RGB-IR ReID模型专注于通过共享特征嵌入、子空间学习或通过对抗学习来弥合RGB和IR图像之间的差距。然而，这些方法没有明确地忽略频谱信息，否则频谱信息与ReID无关。此外，对抗学习方法的收敛性不太有希望。这促使我们设计一种非对抗性的快速解纠缠方法，在学习身份鉴别特征的同时解纠缠频谱信息。为了提取这些特征，我们提出了一种新的网络与解纠缠损失，可以提取身份特征和消除频谱特征。我们的网络有两个分支，频谱消解和频谱提取分支。在谱分解分支上，利用识别损失来学习身份相关的谱分解特征。在频谱提取分支中，我们采用身份消除器损失来欺骗身份分类器，使其主要学习频谱相关信息。整个网络以端到端的方式进行训练，在频谱消除分支上最小化频谱信息，最大化不变身份相关信息。在现有数据集上的大量实验表明，与最先进的方法相比，我们的方法具有上级性能。
Visible-infrared person re-identification (RGB-IR ReID) is extremely important for the surveillance applications under poor illumination conditions. Since the difference in the feature representations not only lies in the person’ pose, viewpoint or illumination variations, but also comes from huge spectrum discrepancy, the task becomes practically very challenging. Existing RGB-IR ReID models focus on bridging the gap between RGB and IR images through shared feature embedding, subspace learning or via adversarial learning. However, these methods do not explicitly disregard the spectrum information which is otherwise irrelevant for ReID. Further, adversarial learning methods has less promising convergence. This motivates us to design a non-adversarial and fast disentanglement method to disentangle the spectrum information while learning the identity discriminative features. To extract these features, we propose a novel network with disentanglement loss which can distill identity features and dispel spectrum features. Our network has two branches, spectrum dispelling and spectrum distilling branch. On spectrum dispelling branch, we apply identification loss to learn the identity related and spectrum disentangled features. On spectrum distilling branch, we apply an identity-dispeller loss to fool the identity classifier so that it primarily learns spectrum related information. The entire network is trained in an end-to-end manner, which minimizes spectrum information and maximizes invariant identity relevant information at spectrum dispelling branch. Extensive experiments on existing datasets demonstrate the superior performance of our approach compared to the state-of-the-art.