Semantic Augmentation in Images using Language

arXiv:2404.02353v1 Announce Type: cross
Abstract: Deep Learning models are incredibly data-hungry and require very large labeled datasets for supervised learning. As a consequence, these models often suffer from overfitting, limiting their ability to generalize to real-world examples. Recent advancements in diffusion models have enabled the generation of photorealistic images based on textual inputs. Leveraging the substantial datasets used to train these diffusion models, we propose a technique to utilize generated images to augment existing datasets. This paper explores various strategies …

abstract arxiv augmentation cs.ai cs.cv cs.lg data datasets deep learning diffusion diffusion models examples images inputs language overfitting photorealistic photorealistic images semantic supervised learning textual type world