Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks

ArXi:2605.11898v1 Announce Type: new Class imbalance is a persistent challenge in visual recognition, particularly in safety-critical domains where collecting positive examples is expensive and rare events are inherently underrepresented. We propose a lightweight synthetic data augmentation pipeline that fine-tunes a LoRA adapter on as few as 20-50 real images of a rare class and uses a pretrained diffusion model to generate synthetic samples for