Building extraction with vision transformer

TL;DR

This paper introduces BuildFormer, a novel Vision Transformer architecture with a dual-path structure for precise building extraction from remote sensing images, addressing CNN limitations in global dependency modeling and detail preservation.

Contribution

The paper proposes BuildFormer, a dual-path Vision Transformer with window-based attention, improving global dependency modeling and spatial detail preservation for remote sensing building extraction.

Findings

Achieved 75.74% IoU on Massachusetts dataset.

Outperformed existing CNN-based methods.

Reduced computational complexity with window-based attention.

Abstract

As an important carrier of human productive activities, the extraction of buildings is not only essential for urban dynamic monitoring but also necessary for suburban construction inspection. Nowadays, accurate building extraction from remote sensing images remains a challenge due to the complex background and diverse appearances of buildings. The convolutional neural network (CNN) based building extraction methods, although increased the accuracy significantly, are criticized for their inability for modelling global dependencies. Thus, this paper applies the Vision Transformer for building extraction. However, the actual utilization of the Vision Transformer often comes with two limitations. First, the Vision Transformer requires more GPU memory and computational costs compared to CNNs. This limitation is further magnified when encountering large-sized inputs like fine-resolution remote sensing images. Second, spatial details are not sufficiently preserved during the feature extraction of the Vision Transformer, resulting in the inability for fine-grained building segmentation. To handle these issues, we propose a novel Vision Transformer (BuildFormer), with a dual-path structure. Specifically, we design a spatial-detailed context path to encode rich spatial details and a global context path to capture global dependencies. Besides, we develop a window-based linear multi-head self-attention to make the complexity of the multi-head self-attention linear with the window size, which strengthens the global context extraction by using large windows and greatly improves the potential of the Vision Transformer in processing large-sized remote sensing images. The proposed method yields state-of-the-art performance (75.74% IoU) on the Massachusetts building dataset. Code will be available.