Low-resolution person re-identification is a challenging task to match low-resolution (LR) probes with high-resolution (HR) gallery images. To address the resolution gap, existing methods typically recover missing details for LR probes by super-resolution, and then match the recovered HR images (instead of the original LR probes) with gallery images. However, they usually pre-specify fixed scale factors for all LR images, and ignore that choosing a preferable scale factor for each image can recover more discriminative content and accordingly benefit the re-id performance. Moreover, these methods do not focus on learning LR representations themselves and always resort to extra recovery to handle LR probes, which is quite time-consuming during inference. To tackle these problems, we propose a Self-supervised Recovery and Guide (SRG) re-id model in this paper. Given LR images during training, our model first recovers more discriminative HR images by finding out preferable scale factors, and further leverages them as guide to improve original LR representations. By enforcing LR representations to approach the self-recovered HR guide in a self-supervised manner, our model can learn more discriminative representations for LR images. As a result, our model is able to directly handle LR probes without requiring recovery during inference, thereby reducing inference time significantly. Extensive experiments demonstrate the effectiveness of our method on four datasets.

中文翻译：

---

低分辨率人员重新识别的自我监督恢复和指南


将低分辨率（LR）探针与高分辨率（HR）图库图像进行匹配，低分辨率行人重新识别是一项具有挑战性的任务。为了解决分辨率差距，现有方法通常通过超分辨率恢复 LR 探头丢失的细节，然后将恢复的 HR 图像（而不是原始 LR 探头）与图库图像进行匹配。然而，他们通常为所有 LR 图像预先指定固定的比例因子，而忽略了为每个图像选择更合适的比例因子可以恢复更具辨别力的内容，从而有利于重新识别性能。此外，这些方法并不专注于学习 LR 表示本身，而是总是依靠额外的恢复来处理 LR 探测，这在推理过程中非常耗时。为了解决这些问题，我们在本文中提出了一种自监督恢复和引导（SRG）重识别模型。在训练期间给定 LR 图像，我们的模型首先通过找出更好的比例因子来恢复更具辨别力的 HR 图像，并进一步利用它们作为改进原始 LR 表示的指导。通过强制 LR 表示以自我监督的方式接近自我恢复的 HR 指南，我们的模型可以学习 LR 图像的更多判别性表示。因此，我们的模型能够直接处理 LR 探针，而无需在推理过程中进行恢复，从而显着缩短推理时间。大量的实验证明了我们的方法在四个数据集上的有效性。