Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classification

Original training images (c) Faithfulness and diversity (b) Diversity (a) Faithfulness Figure 1. Given training images, data augmentation aims to generate new faithful and diverse synthetic images. (a) These synthetic images are faithful but not diverse. (b) These synthetic images are diverse but not faithful. (c) These synthetic images are both faithful and diverse.