GeNIe: Generative Hard Negative Images Through Diffusion

arXiv:2312.02548v2 Announce Type: replace
Abstract: Data augmentation is crucial in training deep models, preventing them from overfitting to limited data. Recent advances in generative AI, e.g., diffusion models, have enabled more sophisticated augmentation techniques that produce data resembling natural images. We introduce GeNIe a novel augmentation method which leverages a latent diffusion model conditioned on a text prompt to merge contrasting data points (an image from the source category and a text prompt from the target category) to generate challenging …

arxiv cs.cv diffusion generative genie images negative through type