Improvement of the Clothes-Changing Person Re-identification with Multiple Loss Functions

Person re-identification plays a crucial role in various domains, such as intelligent transportation, public safety, and smart cities. However, the current person re-identification methods are unable to address the challenges posed by long-term clothes-changing scenarios. As a result, clothes-changing person re-identification has gained increasing attention and is considered a highly challenging task. Most existing works in this area mainly focus on learning from multi-modal information such as outlines and sketches, while overlooking valuable features in the original RGB images. In this paper, we propose a novel method that conducts in-depth research on RGB images. We introduce the Scaled Triplet Loss (STL) for metric learning, which helps similar samples be closer in the feature space and encourages the model to pay more attention to the distances between samples that are difficult to distinguish. In addition, over an existing loss function, we propose Augmentation Clothing-irrelevant Features Loss (ACL), which better exploits features unrelated to clothing in RGB images, resulting in more advanced model performance. Extensive experiments have demonstrated the performance of our model surpasses other state-of-the-art methods in two real-world datasets.