Pixel Level Data Augmentation for Semantic Image Segmentation using Generative Adversarial Networks
This addresses the issue of segmentation accuracy degradation due to label imbalance for computer vision practitioners, but it is incremental as it applies an existing GAN method to a specific data augmentation task.
The paper tackles the problem of unbalanced semantic label distribution in semantic image segmentation by using generative adversarial networks (GANs) for data augmentation, resulting in a 1.3% to 2.1% increase in average segmentation accuracy and improved performance on low-accuracy classes.
Semantic segmentation is one of the basic topics in computer vision, it aims to assign semantic labels to every pixel of an image. Unbalanced semantic label distribution could have a negative influence on segmentation accuracy. In this paper, we investigate using data augmentation approach to balance the semantic label distribution in order to improve segmentation performance. We propose using generative adversarial networks (GANs) to generate realistic images for improving the performance of semantic segmentation networks. Experimental results show that the proposed method can not only improve segmentation performance on those classes with low accuracy, but also obtain 1.3% to 2.1% increase in average segmentation accuracy. It shows that this augmentation method can boost accuracy and be easily applicable to any other segmentation models.