SCANet: Split Coordinate Attention Network for Building Footprint Extraction

TL;DR

SCANet introduces a novel attention module that enhances building footprint extraction from remote sensing images by capturing spatially remote interactions, leading to state-of-the-art performance on benchmark datasets.

Contribution

The paper proposes a new plug-and-play Split Coordinate Attention module that improves semantic feature extraction in CNNs for building footprint extraction.

Findings

SCANet achieves the highest IoU scores of 91.61% and 75.49% on two public datasets.

The SCA module effectively captures spatially remote interactions, enhancing segmentation accuracy.

SCANet outperforms recent state-of-the-art methods in building footprint extraction.

Abstract

Building footprint extraction holds immense significance in remote sensing image analysis and has great value in urban planning, land use, environmental protection and disaster assessment. Despite the progress made by conventional and deep learning approaches in this field, they continue to encounter significant challenges. This paper introduces a novel plug-and-play attention module, Split Coordinate Attention (SCA), which ingeniously captures spatially remote interactions by employing two spatial range of pooling kernels, strategically encoding each channel along x and y planes, and separately performs a series of split operations for each feature group, thus enabling more efficient semantic feature extraction. By inserting into a 2D CNN to form an effective SCANet, our SCANet outperforms recent SOTA methods on the public Wuhan University (WHU) Building Dataset and Massachusetts Building Dataset in terms of various metrics. Particularly SCANet achieves the best IoU, 91.61% and 75.49% for the two datasets. Our code is available at https://github.com/AiEson/SCANet