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

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.

Automated summary

This study investigates class-wise adversarial adaptation networks for the classification of hyperspectral remote sensing images. By adversarial learning between feature extractor and multiple domain discriminators, domain-invariant features are generated, and a probability-prediction MMD method is introduced to improve feature-alignment performance. The proposed CDA network can achieve unsupervised classification of target images and has demonstrated efficiency in experiments using Hyperion and AVIRIS hyperspectral data.