Expediting Building Footprint Extraction from High-resolution Remote Sensing Images via progressive lenient supervision

TL;DR

This paper introduces BFSeg, an efficient building footprint segmentation framework that improves learning speed and accuracy from high-resolution remote sensing images by using a novel decoder design and lenient supervision strategies.

Contribution

The paper proposes a densely-connected coarse-to-fine decoder and a lenient deep supervision method, significantly enhancing transferability and efficiency of building segmentation models.

Findings

BFSeg outperforms prior methods in accuracy and efficiency.

The proposed decoder facilitates fast multi-scale feature fusion.

Lenient supervision improves learning in hybrid regions.

Abstract

The efficacy of building footprint segmentation from remotely sensed images has been hindered by model transfer effectiveness. Many existing building segmentation methods were developed upon the encoder-decoder architecture of U-Net, in which the encoder is finetuned from the newly developed backbone networks that are pre-trained on ImageNet. However, the heavy computational burden of the existing decoder designs hampers the successful transfer of these modern encoder networks to remote sensing tasks. Even the widely-adopted deep supervision strategy fails to mitigate these challenges due to its invalid loss in hybrid regions where foreground and background pixels are intermixed. In this paper, we conduct a comprehensive evaluation of existing decoder network designs for building footprint segmentation and propose an efficient framework denoted as BFSeg to enhance learning efficiency and effectiveness. Specifically, a densely-connected coarse-to-fine feature fusion decoder network that facilitates easy and fast feature fusion across scales is proposed. Moreover, considering the invalidity of hybrid regions in the down-sampled ground truth during the deep supervision process, we present a lenient deep supervision and distillation strategy that enables the network to learn proper knowledge from deep supervision. Building upon these advancements, we have developed a new family of building segmentation networks, which consistently surpass prior works with outstanding performance and efficiency across a wide range of newly developed encoder networks.