Enhancing Image Classification Performance via GAN-based Data Augmentation

This paper presents a novel data augmentation strategy that combines GAN-generated samples with optimized sampling to address class imbalance in image classification. Our approach significantly enhances classification accuracy on the CIFAR-10 dataset, achieving a 99.79% accuracy ratean improvement of 43.57 percentage points over the baseline. Compared to traditional augmentation methods, our strategy better mitigates class imbalance and improves dataset diversity. Further validation on MNIST and STL-10 confirms the generalizability of our method.