Interpretable Attributed Scattering Center Extracted via Deep Unfolding

• Published in: IEEE International Geoscience and Remote Sensing Symposium proceedings pp. 2004 - 2008
• Main Authors: Yang, Haodong, Huang, Zhongling, Zhang, Zhe
• Format: Conference Proceeding
• Language: English
• Published: IEEE 07.07.2024
• Subjects: Attributed Scattering Center; Deep Unfolding; Dictionaries; Geoscience and remote sensing; Iterative algorithms; Neural networks; Reliability; Scattering; Sparse approximation; Sparse Representation
• ISSN: 2153-7003
• DOI: 10.1109/IGARSS53475.2024.10641709

Most existing sparse representation based approaches for attributed scattering center (ASC) extraction adopt traditional iterative optimization algorithms, which suffer from lengthy computation time and limited precision. This paper presents a solution by introducing an interpretable network that can effectively and rapidly extract ASC via deep unfolding. Initially, we create a dictionary containing reliable prior knowledge and apply it to iterative shrinkage-thresholding algorithm (ISTA). Then, we unfold ISTA to a neural network, employing it to autonomously and precisely optimize the hyperparameters. The interpretability in physics is retained by applying a dictionary with physical meaning. The experiments are conducted on multiple test sets with diverse data distribution and demonstrate the superior performance and generalizability of our method.