Unsupervised Domain Adaptation for Cross-Scene Hyperspectral Image Classification Based on Decoupled Contrastive Learning

Jiaxin Zhang, Mingyang Zhang, Maoguo Gong, Fenlong Jiang, Xiangming Jiang, Yu Zhou, Dan FengIJCNN 2024 · OpenReview

Abstract

Recent studies have highlighted the effectiveness of deep domain adaptation (DA) techniques in addressing cross-scene hyperspectral image (HSI) classification challenges. However, most of the existing DA methods often prioritize aligning data distributions while overlooking the intrinsic separability between source and target domain data. In this paper, we propose a decoupled contrastive learning based unsupervised domain adaptation (DCLUDA) method for HSI classification. Unlike conventional adversarial DA methods, our method introduces a unique DA loss specifically designed to minimize class confusion in the target domain. This not only simplifies model training but also enhances class discriminability. Moreover, we employ a decoupled contrastive learning strategy on both domains to enhance data separability within each domain. Finally, we propose a sample selection strategy based on confident learning to select high-confidence samples from the target domain for fine-tuning the DA model. Experiments on two cross-scene HSI classification tasks shown that our proposed DCLUDA outperforms several existing DA methods.
BibTeX
@inproceedings{zhang2024unsupervised,
  author = {Jiaxin Zhang and Mingyang Zhang and Maoguo Gong and Fenlong Jiang and Xiangming Jiang and Yu Zhou and Dan Feng},
  title = {{Unsupervised Domain Adaptation for Cross-Scene Hyperspectral Image Classification Based on Decoupled Contrastive Learning}},
  booktitle = {IJCNN},
  year = {2024},
  url = {https://openreview.net/forum?id=XQLV8wXehi},
}

Loading related content...

Figure