Semantic Segmentation of Remote Sensing Images with Sparse Annotations
This work aims to reduce the annotation burden for researchers and practitioners working with remote sensing image segmentation, making the process more efficient.
This paper addresses the challenge of training CNNs for semantic segmentation of very high resolution remote sensing images, which typically require extensive pixel-level annotations. The authors propose a framework that utilizes sparse, scribble-based annotations, complemented by a method called FESTA that incorporates unsupervised learning signals from spatial and feature neighborhood structures.
Training Convolutional Neural Networks (CNNs) for very high resolution images requires a large quantity of high-quality pixel-level annotations, which is extremely labor- and time-consuming to produce. Moreover, professional photo interpreters might have to be involved for guaranteeing the correctness of annotations. To alleviate such a burden, we propose a framework for semantic segmentation of aerial images based on incomplete annotations, where annotators are asked to label a few pixels with easy-to-draw scribbles. To exploit these sparse scribbled annotations, we propose the FEature and Spatial relaTional regulArization (FESTA) method to complement the supervised task with an unsupervised learning signal that accounts for neighbourhood structures both in spatial and feature terms.