Category Semantic-Guided Unsupervised Domain Adaptation Network for Hyperspectral Image Classification

Binge Cui, Shihan Huang, Guangbo Ren, Haojie Li, Jianzhi Yu

Abstract: Domain adaptation methods enable model migration and adaptation across different domain data distributions. However, the source and target domains of hyperspectral images (HSIs) have large spectral offsets and spatial distribution differences, making the extraction of high-quality domain-invariant features between different domains essential for classification. To achieve a more consistent feature representation for each category between the source and target domains, we propose a category semantic-guided network (CSGNet) unsupervised domain adaptation (UDA) for HSI classification. CSGNet is designed to learn cross-domain invariant representation from category semantic information. First, to embed category semantic prior knowledge during feature learning, we extracted textual semantic features from the textual descriptions for each category and projected visual features into the semantic space via visual-linguistic alignment. A category representation memory pool is then introduced to store the visual-linguistic representations of different categories. Second, we propose a biclassifier adversarial learning (BCAL) method designed to generate inconsistent category predictions in the unlabeled target domain, thereby enhancing the classifier’s discriminative capability regarding those hard-to-transfer features. Finally, to utilize the domain-invariant features stored in the category memory pool, a category attention (CA) module is proposed to guide the model’s adaptation to the data from different domains, mitigating the impact of the differences in the domain data distributions. Extensive experimental results validated on three cross-domain datasets demonstrate that the proposed method outperforms other state-of-the-art methods. The source code is available at http://github.com/cuibinge/CSGNet

External IDs:dblp:journals/tgrs/CuiHRLY25