AI RESEARCH
Cross-Domain Adversarial Augmentation: Stabilizing GANs for Medical and Handwriting Data Scarcity
arXiv CS.CV
•
ArXi:2605.01815v1 Announce Type: new Generative Adversarial Networks (GANs) offer a pragmatic route to mitigate data scarcity in vision tasks. We study generative augmentation across two low-resource domains: Bangla handwritten characters and chest X-ray imaging using DCGAN-style models trained at 64x64 resolution. We evaluate fidelity and diversity via Inception Score (IS), Fr'echet Inception Distance (FID), and embedding visualizations (t-SNE/UMAP), and assess downstream utility by