Using GANs to Augment Data for Cloud Image Segmentation Task

TL;DR

This paper explores using GANs to generate additional training data for cloud image segmentation, improving model accuracy despite limited labeled datasets.

Contribution

It introduces a method to generate and estimate ground-truth maps for synthetic images, enhancing segmentation training with augmented data.

Findings

GAN-augmented data improves segmentation accuracy

Effective estimation of ground-truth maps for synthetic images

Validation with statistical techniques confirms effectiveness

Abstract

While cloud/sky image segmentation has extensive real-world applications, a large amount of labelled data is needed to train a highly accurate models to perform the task. Scarcity of such volumes of cloud/sky images with corresponding ground-truth binary maps makes it highly difficult to train such complex image segmentation models. In this paper, we demonstrate the effectiveness of using Generative Adversarial Networks (GANs) to generate data to augment the training set in order to increase the prediction accuracy of image segmentation model. We further present a way to estimate ground-truth binary maps for the GAN-generated images to facilitate their effective use as augmented images. Finally, we validate our work with different statistical techniques.