What brings the performance difference in Deep Learning with different data augmentation strategies?

Question

I am studying the performance of deep learning models toward abnormality detection in chest X-rays.

Due to sparsity of data, I augment the data using different augmentation strategies including:

• Traditional augmentation methods (Gaussian smoothing, unsharp masking, and minimum filtering)
• Generative Adversarial Networks

Contrary to the existing literature, I find that the models showed promising results with traditional augmentation methods (that i have mentioned herewith) than with GAN-generated synthetic images.

What brings this performance difference?