Supervised domain adaptation for building extraction from off-nadir aerial images

TL;DR

This paper introduces a supervised domain adaptation approach for building extraction from off-nadir aerial images, improving accuracy over existing teacher-student methods by leveraging lightweight encoder-decoder networks and extensive benchmarking.

Contribution

It proposes a novel supervised domain adaptation method for encoder-decoder networks using lightweight encoders, outperforming teacher-student learning approaches in building extraction tasks.

Findings

SDA significantly outperforms KD and DML in F1 scores across building types.

Extensive benchmarking identifies the best EDN architecture for SDA.

The method enhances robustness of CNNs for urban building extraction.

Abstract

Building extraction $-$ needed for inventory management and planning of urban environment $-$ is affected by the misalignment between labels and off-nadir source imagery in training data. Teacher-Student learning of noise-tolerant convolutional neural networks (CNNs) is the existing solution, but the Student networks typically have lower accuracy and cannot surpass the Teacher's performance. This paper proposes a supervised domain adaptation (SDA) of encoder-decoder networks (EDNs) between noisy and clean datasets to tackle the problem. EDNs are configured with high-performing lightweight encoders such as EfficientNet, ResNeSt, and MobileViT. The proposed method is compared against the existing Teacher-Student learning methods like knowledge distillation (KD) and deep mutual learning (DML) with three newly developed datasets. The methods are evaluated for different urban buildings (low-rise, mid-rise, high-rise, and skyscrapers), where misalignment increases with the increase in building height and spatial resolution. For a robust experimental design, 43 lightweight CNNs, five optimisers, nine loss functions, and seven EDNs are benchmarked to obtain the best-performing EDN for SDA. The SDA of the best-performing EDN from our study significantly outperformed KD and DML with up to 0.943, 0.868, 0.912, and 0.697 F1 scores in the low-rise, mid-rise, high-rise, and skyscrapers respectively. The proposed method and the experimental findings will be beneficial in training robust CNNs for building extraction.