Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification
This addresses scalability and generalization issues in person re-identification for surveillance and security applications, but it is an incremental improvement over existing augmentation techniques.
The paper tackles the problem of limited pose and viewpoint diversity in person re-identification datasets by proposing Pose-dIVE, a data augmentation method using diffusion models to generate diverse training examples, which improves model generalization and reduces bias.
Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across images. Existing datasets frequently lack diversity and scalability in these aspects, hindering the generalization of Re-ID models to new camera systems. We propose Pose-dIVE, a novel data augmentation approach that incorporates sparse and underrepresented human pose and camera viewpoint examples into the training data, addressing the limited diversity in the original training data distribution. Our objective is to augment the training dataset to enable existing Re-ID models to learn features unbiased by human pose and camera viewpoint variations. To achieve this, we leverage the knowledge of pre-trained large-scale diffusion models. By conditioning the diffusion model on both the human pose and camera viewpoint concurrently through the SMPL model, we generate training data with diverse human poses and camera viewpoints. Experimental results demonstrate the effectiveness of our method in addressing human pose bias and enhancing the generalizability of Re-ID models compared to other data augmentation-based Re-ID approaches.