Conditional Data Augmentation For Sky Segmentation

Abstract

Outdoor scene parsing is a very popular topic which algorithms seek to labels or identify objects in images. Sky segmentation is one of the popular outdoor scene parsing task. Sky segmentation models are usually trained on ideal datasets and produce high quality results. However, the performance of sky segmentation model decreases because of varying weather conditions, different time and scene changes due to seasonal weather or other issues in reality. This paper focuses on applying data augmentation methods to generate diversified images. A conditional data augmentation method based on BicycleGAN is proposed in this paper. The model considers mask loss and content loss for improving the quality and details of the generated images. The experimental results demonstrate that the quality of the generated image is better than the existing methods.