Building Type Classification Using CNN-Transformer Cross-Encoder Adaptive Learning From Very High Resolution Satellite Images

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 18; pp. 976 - 994
• Main Authors: Zhang, Shaofeng, Li, Mengmeng, Zhao, Wufan, Wang, Xiaoqin, Wu, Qunyong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Architecture; Artificial neural networks; Attention; Boundaries; Building type classification; Buildings; Classification; CNN-transformer networks; Coders; cross-encoder; Datasets; Earth; Feature extraction; feature interaction; High resolution; Image enhancement; Image resolution; Machine learning; Modules; Neural networks; Optimization; Remote sensing; Satellite imagery; Semantics; Transformers; Urban environments; very high resolution remote sensing; Visual discrimination learning; Visual perception; Visualization

Building type information indicates the functional properties of buildings and plays a crucial role in smart city development and urban socioeconomic activities. Existing methods for classifying building types often face challenges in accurately distinguishing buildings between types while maintaini...