Cross-Domain Adversarial Augmentation: Stabilizing GANs for Medical and Handwriting Data Scarcity

TL;DR

This paper investigates stabilizing GANs for data augmentation in low-resource medical and handwriting imaging, demonstrating improved classification performance through synthetic data and stability techniques.

Contribution

It introduces a simple, reproducible GAN-based augmentation method with stability enhancements for medical and handwriting data scarcity.

Findings

Synthetic augmentation improves classification accuracy in limited-data scenarios.

Stability techniques like gradient penalty and spectral normalization enhance GAN training.

The approach provides a strong baseline for generative augmentation in resource-constrained imaging.

Abstract

Generative Adversarial Networks (GANs) can help overcome data scarcity in computer vision tasks by generating additional training samples. In this work, we explore generative data augmentation in two low-resource domains: Bangla handwritten character recognition and chest X-ray image analysis. We use DCGAN-based models trained on 64x64 images to generate synthetic samples and evaluate their quality using Inception Score (IS), Fr\'echet Inception Distance (FID), and visualization methods such as t-SNE and UMAP. To measure practical usefulness, we train image classifiers using real data and a combination of real and synthetic data. Experimental results show that synthetic augmentation improves data diversity and consistently increases classification performance in limited-data settings. We also investigate training stability techniques, including gradient penalty and spectral normalization, and perform ablation studies on synthetic-to-real data ratios and sample filtering strategies. In addition, we discuss challenges related to medical image evaluation, dataset licensing, and privacy concerns of synthetic data. Our approach is simple, reproducible, and provides a strong baseline for generative augmentation in resource-constrained imaging applications.