RGB-Infrared (RGB-IR) person re-identification (ReID) is a technology where the system can automatically identify the same person appearing at different parts of a video when light is unavailable. The critical challenge of this task is the cross-modality gap of features under different modalities. To solve this challenge, we proposed a Teacher-Student GAN model (TS-GAN) to adopt different domains and guide the ReID backbone. (1) In order to get corresponding RGB-IR image pairs, the RGB-IR Generative Adversarial Network (GAN) was used to generate IR images. (2) To kick-start the training of identities, a ReID Teacher module was trained under IR modality person images, which is then used to guide its Student counterpart in training. (3) Likewise, to better adapt different domain features and enhance model ReID performance, three Teacher-Student loss functions were used. Unlike other GAN based models, the proposed model only needs the backbone module at the test stage, making it more efficient and resource-saving. To showcase our model’s capability, we did extensive experiments on the newly-released SYSU-MM01 and RegDB RGB-IR Re-ID benchmark and achieved superior performance to the state-of-the-art with 47.4% mAP and 69.4% mAP respectively.

RGB-红外 (RGB-IR) 人员重新识别 (ReID) 是一项技术，当光线不可用时，系统可以自动识别出现在视频不同部分的同一个人。这项任务的关键挑战是不同模态下特征的跨模态差距。为了解决这一挑战，我们提出了一种教师-学生 GAN 模型（TS-GAN）来采用不同的领域并指导 ReID 主干。(1)为了得到相应的RGB-IR图像对，使用RGB-IR生成对抗网络(GAN)生成IR图像。(2) 为了启动身份训练，在 IR 模态人物图像下训练了一个 ReID 教师模块，然后用于指导其学生对应方进行训练。(3) 同样，为了更好地适应不同领域的特征，增强模型 ReID 性能，使用了三个师生损失函数。与其他基于 GAN 的模型不同，所提出的模型在测试阶段只需要主干模块，使其更加高效和节省资源。为了展示我们模型的能力，我们对新发布的 SYSU-MM01 和 RegDB RGB-IR Re-ID 基准进行了大量实验，并分别以 47.4% 的 mAP 和 69.4% 的 mAP 取得了优于最先进技术的性能。