Semantic Augmentation in Images using Language
This addresses the data scarcity issue in supervised learning for AI practitioners, but it appears incremental as it builds on existing diffusion model advancements.
The paper tackles the problem of deep learning models overfitting due to limited labeled data by proposing a technique that uses diffusion models to generate images for data augmentation, aiming to improve out-of-domain generalization.
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 for effective data augmentation to improve the out-of-domain generalization capabilities of deep learning models.