Class-Wise Distribution Adaptation for Unsupervised Classification of Hyperspectral Remote Sensing Images

• Published in: IEEE transactions on geoscience and remote sensing Vol. 59; no. 1; pp. 508 - 521
• Main Authors: Liu, Zixu, Ma, Li, Du, Qian
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-01-2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adversarial learning; Classification; Discriminators; Distribution; domain adaptation; Domains; Feature extraction; Gallium nitride; Generative adversarial networks; Hyperspectral imaging; Image classification; Infrared imaging; Infrared spectrometers; Neural networks; Probability theory; Remote sensing; Target recognition
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2020.2997863

Class-wise adversarial adaptation networks are investigated for the classification of hyperspectral remote sensing images in this article. By adversarial learning between the feature extractor and the multiple domain discriminators, domain-invariant features are generated. Moreover, a probability-prediction-based maximum mean discrepancy (MMD) method is introduced to the adversarial adaptation network to achieve a superior feature-alignment performance. The class-wise adversarial adaptation in conjunction with the class-wise probability MMD is denoted as the class-wise distribution adaptation (CDA) network. The proposed CDA does not require labeled information in the target domain and can achieve an unsupervised classification of the target image. The experimental results using the Hyperion and Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) hyperspectral data demonstrated its efficiency.