Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery

TL;DR

This paper introduces FarSeg, a novel foreground-aware relation network designed to improve geospatial object segmentation in high-resolution remote sensing images by addressing foreground-background imbalance and intra-class variance.

Contribution

It proposes a relation-based and optimization-based foreground modeling approach, enhancing discrimination and training focus on foreground and hard background examples.

Findings

Outperforms state-of-the-art segmentation methods on large-scale datasets

Achieves a better balance between speed and accuracy

Demonstrates robustness to scale variation and background complexity

Abstract

Geospatial object segmentation, as a particular semantic segmentation task, always faces with larger-scale variation, larger intra-class variance of background, and foreground-background imbalance in the high spatial resolution (HSR) remote sensing imagery. However, general semantic segmentation methods mainly focus on scale variation in the natural scene, with inadequate consideration of the other two problems that usually happen in the large area earth observation scene. In this paper, we argue that the problems lie on the lack of foreground modeling and propose a foreground-aware relation network (FarSeg) from the perspectives of relation-based and optimization-based foreground modeling, to alleviate the above two problems. From perspective of relation, FarSeg enhances the discrimination of foreground features via foreground-correlated contexts associated by learning foreground-scene relation. Meanwhile, from perspective of optimization, a foreground-aware optimization is proposed to focus on foreground examples and hard examples of background during training for a balanced optimization. The experimental results obtained using a large scale dataset suggest that the proposed method is superior to the state-of-the-art general semantic segmentation methods and achieves a better trade-off between speed and accuracy. Code has been made available at: \url{https://github.com/Z-Zheng/FarSeg}.