A Unified Approach for Binary-Class and Multi-Class Data Augmented Generation

Deep neural networks excel in a wide range of tasks but require diverse datasets to prevent overfitting. Overfitting occurs when a network fits training data too precisely, leading to poor generalization. Data Augmentation is often used to mitigate overfitting aiming at enlarging and improving the quality of training datasets, facilitating the construction of superior deep learning models. MAGAN algorithm emerges as an innovative approach that functions as a Meta-Analysis of Generative Adversarial Networks (GANs). MAGAN harnesses the latent space capabilities of GANs to confront the challenges presented by binary-class, multi-class, grayscale, and RGB images, effectively covering a wide spectrum of scenarios. In this paper, we propose the use of MAGAN algorithm for binary-class and multi-class data augmented generation. We also undertake an in-depth experimental analysis, evaluating the performance of the proposed MAGAN-based approach in comparison to two alternative baseline scenarios: one without any augmentation and another utilizing a conventional augmentation method. To gauge the effectiveness of the proposed technique, we employed diverse classification metrics, including accuracy, loss, precision, recall, F1-score, and the confusion matrix. Our results demonstrate that the proposed approach surpasses the other two scenarios achieving improvements in terms of accuracy by a factor of x1.15 and x1.03, respectively. This underscores the significant advantages of harnessing MAGAN, a meta-analysis of GANs, for data augmentation across a range of image types and classification tasks.