Data Augmentation for Image Classification Using Generative AI

• Published in: Proceedings / IEEE Workshop on Applications of Computer Vision pp. 4173 - 4182
• Main Authors: Rahat, Fazle, Hossain, M Shifat, Ahmed, Md Rubel, Jha, Sumit Kumar, Ewetz, Rickard
• Format: Conference Proceeding
• Language: English
• Published: IEEE 26.02.2025
• Subjects: Computational modeling; Computer vision; Data augmentation; Data models; diffusion model; Diffusion models; Generative AI; Image classification; Image segmentation; Large language models; llm; subject corruption; Translation
• ISSN: 2642-9381
• DOI: 10.1109/WACV61041.2025.00410

Scaling laws dictate that the performance of AI models is proportional to the amount of available data. Data augmentation is a promising solution to expanding the dataset size. Traditional approaches focused on augmentation using rotation, translation, and resizing. Recent approaches use generative AI models to improve dataset diversity. However, the generative methods struggle with issues such as subject corruption and the introduction of irrelevant artifacts. In this paper, we propose the Automated Generative Data Augmentation (AGA). The framework combines the utility of large language models (LLMs), diffusion models, and segmentation models to augment data. AGA preserves foreground authenticity while ensuring background diversity. Specific contributions include: i) segment and superclass based object extraction, ii) prompt diversity with combinatorial complexity using prompt decomposition, and iii) affine subject manipulation. We evaluate AGA against state-of-the-art (SOTA) techniques on three representative datasets, ImageNet, CUB and iWildCam. The experimental evaluation demonstrates an accuracy improvement of 15.6% and 23.5% for in and out-of-distribution data compared to baseline models respectively. There is also 64.3% improvement in SIC score compared to the baselines.