Skip to content

KHLDGNet: Knowledge-Driven Hierarchical Language-Aware Domain Generalization Network for Cross-Scene Wetland Hyperspectral Image Classification

2026 · IEEE Transactions on Geoscience and Remote Sensing · Vol 64, pp. 5524717-5524717 · 0 citations · 41 references

Abstract

Wetlands are fragile yet vital ecosystems that require precise remote sensing (RS) mapping. Hyperspectral image (HSI) provides high spectral resolution for fine-scale wetland classification, but cross-scene application suffers from domain shifts and a lack of model interpretability. To address these issues, this article proposes a knowledge-driven hierarchical language-aware domain generalization network (KHLDGNet) for interpretable cross-scene wetland HSI classification. Unlike existing vision–language methods that merely use category names or simple attributes as auxiliary text, the core innovation of our framework is the construction of a structured, four-level geographic knowledge hierarchy that encompasses conceptual, rule, instance, and causal. This hierarchy transforms a geographical cognitive framework into computable semantic constraints, guiding the model from superficial pattern matching to deep mechanistic understanding. A MixStyle module in the visual encoder implicitly diversifies feature-level styles to counter spectral and textural variations. Visual and textual features are aligned in a shared semantic space via supervised contrastive learning, unifying generalization and interpretability. Experiments on three real-world wetland datasets demonstrate that KHLDGNet significantly outperforms state-of-the-art domain generalization (DG) methods. Visualization and case studies confirm its semantic explanation capability, contributing to explainable geographic AI (XGeoAI). Code available at https://github.com/SYFYN0317/KHLDGNet

View source

Similar papers

Open access 2026

SemReNet: Semantic Relational Supervision for Domain Generalization in Hyperspectral Image Classification

SemReNet is proposed, a semantic relation-preserving framework that replaces independent anchor alignment with class-level semantic relational supervision for cross-domain hyperspectral classification and achieves overall accuracies of 84.21%, 88.78%, and 84.87%, outperforming the best competing methods.

Qing-Hao Li, Bin-Ge Cui, Guang-Bo Ren et al. · 0 citations
Open access Sep 2026

Dual-Branch GCN-Mamba Network with Semantic-Guided Meta-Learning for Multimodal Remote Sensing Classification

SGML-net is proposed, a semantic-guided meta-learning framework that combines dual-stream feature extraction, adaptive feature fusion and a collaborative GCN-Mamba representation module and a two-stage training strategy that first meta-learns task-adaptive semantic priors and then uses them as stable guidance for globa...

Hao-Dong Zhou, Chen Chen, Yu Liu et al. · 0 citations
2026

Toward Zero-Forgetting: A Training-Free Multimodal Framework for Remote Sensing Class-Incremental Learning

Existing class-incremental learning (CIL) methods for remote sensing (RS) scene classification often tend to be training-intensive or rely on static visual features that may inadequately capture the complex interclass similarity and intraclass diversity inherent in RS imagery. Moreover, directly reusing features from m...

Wen-Liang Du, Ji-Cun He, Jia-Qi Zhao et al. · 0 citations
Sep 2026

LLFA-Net: a collaborative CNN-transformer framework for land cover classification using high-resolution remote sensing images

Experimental results on the ISPRS Potsdam and Vaihingen benchmark datasets show that the proposed CNN-Transformer model attains highly competitive segmentation performance while maintaining computational efficiency.

Wambugu Naftaly, Rui-Sheng Wang, Bo Guo et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.