Dataset: Train, Test, Re-evaluate: Schedule-Sensitive Evaluation of Generative Data for Hand Detection

Tests whether region-localised generative inpainting -- editing only the hand region of a real photo to add gloves, jewellery, or tattoos -- produces data that improves *real* hand detectors at deployment.Measured with paired/unpaired image metrics and six experiments (A-F), four of which involve YOLOv8n training (A, C, D, E) with three seeds each.https://github.com/atmikabhardwaj/Schedule_Sensitive_Evaluation_of_Generative_Data.git