Generating Synthetic Training Datasets using Conditional Generative Adversarial Network to Improve Images Segmentation

Abstract

Limited amount of training datasets in deep learning research could impact the accuracy of the resulting models. This situation can cause overfit, so the model cannot work correctly. A conditional Generative Adversarial Network (CGAN) was introduced to generate synthetic data by considering certain conditions. This study aims to generate additional synthetic training datasets to improve the accuracy of the object segmentation model of images. Firstly, we evaluated CGAN-based dataset generator accuracy against several open datasets. Then, we applied the generator to train two object segmentation models, i.e., FCN and CNN U-Net. Our evaluation shows that CGAN can generate synthetic datasets well. Complex datasets require more training iterations. It also improves the validation loss and validation accuracy of both segmentation models, although other metrics still need further improvement