Benchmarking attention mechanisms and consistency regularization semi-supervised learning for post-flood building damage assessment

Rapid and accurate building damage assessment (BDA) following floods is critical for effective disaster response, yet faces challenges from limited labeled data and subtle damage cues in satellite imagery. Existing deep learning change detection (CD) methods may exhibit low recall or misclassify damage inappropriately when transferred directly to the post-flood BDA (Flood-BDA) task. This study addresses these gaps by establishing the first systematic benchmark evaluating both supervised CD model transfer and semi-supervised learning (SSL) specifically for Flood-BDA. This research investigate image-level consistency regularization SSL to combat data scarcity, finding that strategies using pseudo-label derived reference distributions significantly enhance performance (+1.17% avg. Kappa at 5% labels). Notably, pseudo-label outperform ground-truth label strategies in low-label settings (e.g., +4.84% Kappa at 5% labels). Furthermore, confronting the limitations of transferred CD models (low recall, misclassifying ’destroyed’ as ’no damage’), this paper proposed a simple prior attention disaster assessment Net (SPADANet), a lightweight U-Net incorporating a simple prior attention module designed for Flood-BDA. SPADANet demonstrably improves recall (+9.22% over best CD baseline) and exhibits more favorable error patterns for Flood-BDA, despite a precision trade-off. This work provides crucial benchmarks, validates the need for recall-driven, DA-specific designs distinct from CD, and demonstrates the potential of prior attention and image-level consistency regularization for post-flood building damage assessment. The code will be available at https://github.com/JX-OctoNeko/Flood_BDA_benchmark.git • First benchmark for Flood BDA, bridging CD-DA gaps on data characteristic. • Tests SSL performance, showing pseudo-labels enhance low-label scenarios. • Proposes SPADANet, validating adaptability to DA tasks via prior attention

Benchmarking · Business · Flood myth · Geography · Machine learning · Anomaly Detection Techniques and Applications · Computer Science · Engineering · Environmental Science · Flood Risk Assessment and Management · Infrastructure Maintenance and Monitoring · Artificial Intelligence

• Learning from Imbalanced Data

  Open Access•Haibo He, Haibo He Haibo He et al.•IEEE Transactions on Knowledge…•2009

  Add to list

• A Survey on Transfer Learning

  Open Access•Sinno Jialin Pan, Qiang Yang•IEEE Transactions on Knowledge…•2010

  Add to list

• Flood vulnerability assessment of urban buildings based on integrating high-resolution remote sensing and street view images

  Open Access•Ziyao Xing, Shuai Yang et al.•Sustainable Cities and Society•2023

  Add to list