Advancing Self-Supervised Learning for Building Change Detection and Damage Assessment: Unified Denoising Autoencoder and Contrastive Learning Framework

• Published in: Remote sensing (Basel, Switzerland) Vol. 17; no. 15; p. 2717
• Main Authors: Yang, Songxi, Peng, Bo, Sui, Tang, Wu, Meiliu, Huang, Qunying
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2025
• Subjects: Accuracy; Change detection; Classification; contrastive learning; Damage assessment; Damage detection; Datasets; Deep learning; Disaster management; Disasters; Feature extraction; Learning; Machine learning; Noise reduction; Performance evaluation; Remote sensing; Representations; Segmentation; Self-supervised learning; Semantics; Urban development; Urban environments; vision transformer

Building change detection and building damage assessment are two essential tasks in post-disaster analysis. Building change detection focuses on identifying changed building areas between bi-temporal images, while building damage assessment involves segmenting all buildings and classifying their dam...