Xincheng Shi

Learning What to Generate: A Reinforcement Learning-based Closed-Loop Augmentation Framework for Person Re-identification

Person re-identification (ReID) models are sensitive to long-tail nuisances (e.g., rare viewpoints, occlusions, complex backgrounds), yet current generative augmentation is largely open-loop: prompts/conditions are sampled heuristically without verifying whether the synthesized samples improve ReID …