You can find below (in arXiv format) our recent work on “Advances in Diffusion Models for Image Data Augmentation: A Review of Methods, Models, Evaluation Metrics and Future Research Directions”, authored by P. Alimisis, I. Mademlis, P. Radoglou-Grammatikis, P. Sarigiannidis and G. Th. Papadopoulos.
Image data augmentation constitutes a critical methodology in modern computer vision tasks, since it can facilitate towards enhancing the diversity and quality of training datasets; thereby, improving the performance and robustness of machine learning models in downstream tasks.
The study realizes a systematic and in-depth review of DM-based approaches for image augmentation, including:
- A comprehensive analysis of the fundamental principles, model architectures and training strategies of diffusion models
- A taxonomy of the relevant image augmentation methods (focusing on techniques regarding semantic manipulation, personalization and adaptation, and application-specific augmentation tasks)
- Performance assessment methodologies and respective evaluation metrics
- Current challenges and future research directions in the field.