Dual-Intervention-Constrained Mask-Adversary Framework for Unsupervised Domain Adaptation of Hyperspectral Image Classification

Chunyan Yu, Xu Mingyang, Qiang Zhang, Xiaoqiang LuIEEE GRSL 2024 · DOI

Abstract

To mitigate the domain shift and enhance the alignment of the spatial-spectral features, this letter proposes a novel dual-intervention-constrained mask-adversary (DICMA) framework for unsupervised domain adaptation (UDA) of hyperspectral image classification (HSIC). Innovatively, DICMA integrates a generator, masker, and bi-classifier within an adversarial framework constrained by a dual intervention mechanism. Specifically, the correlation intervention module (CIM) ensures the preservation and independence of causal spatial-spectral variables, while the knowledge distillation intervention module completes the spatial-spectral generalization with constrained distillation information. Besides, with the collaborative adversarial training strategy, the proposed approach transfers effective knowledge for spatial-spectral feature alignment. Experimental results and analyses demonstrate the effectiveness of the proposed DICMA model, which yields an accuracy of 91.15% in the Pavia University (PaviaU) <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\to $ </tex-math></inline-formula> Pavia Center (PaviaC). Our code will be released at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Chirsycy/DICMA</uri>.
BibTeX
@article{yu2024dual,
  author = {Chunyan Yu and Xu Mingyang and Qiang Zhang and Xiaoqiang Lu},
  title = {{Dual-Intervention-Constrained Mask-Adversary Framework for Unsupervised Domain Adaptation of Hyperspectral Image Classification}},
  journal = {IEEE Geoscience and Remote Sensing Letters},
  year = {2024},
  doi = {10.1109/lgrs.2024.3451180},
}

Loading related content...

Figure