论文标题
基于教师模型和对抗性培训的照明自适应人REID
Illumination adaptive person reid based on teacher-student model and adversarial training
论文作者
论文摘要
大多数现有的作品亲自重新识别（REID）专注于照明保持相同或几乎没有波动的设置。但是，照明程度的变化可能会显着影响REID算法的鲁棒性。为了解决这个问题，我们提出了一个两流网络，该网络可以将REID功能与照明功能分开以增强REID性能。它的创新是三重的：（1）判别性熵损失，以确保REID功能不包含照明信息。 （2）在“中性”照明条件下训练图像的REID教师模型，以指导REID分类。 （3）通过照明调整和原始图像之间的差异来培训的照明教师模型，以指导照明分类。我们通过在两个最受欢迎的REID基准中合成一组预定义的照明条件来构建两个增强数据集：Market1501和Dukemtmc-Reid。实验表明，我们的算法的表现优于其他最先进的作品，并且在极低光下处理图像方面尤其有效。
Most existing works in Person Re-identification (ReID) focus on settings where illumination either is kept the same or has very little fluctuation. However, the changes in the illumination degree may affect the robustness of a ReID algorithm significantly. To address this problem, we proposed a Two-Stream Network that can separate ReID features from lighting features to enhance ReID performance. Its innovations are threefold: (1) A discriminative entropy loss to ensure the ReID features contain no lighting information. (2) A ReID Teacher model trained by images under "neutral" lighting conditions to guide ReID classification. (3) An illumination Teacher model trained by the differences between the illumination-adjusted and original images to guide illumination classification. We construct two augmented datasets by synthetically changing a set of predefined lighting conditions in two of the most popular ReID benchmarks: Market1501 and DukeMTMC-ReID. Experiments demonstrate that our algorithm outperforms other state-of-the-art works and particularly potent in handling images under extremely low light.
