Cross-domain Hyperspectral Image Classification based on Bi-directional Domain Adaptation

2025-07-02

AI Summary

To address spectral shift of the same land-cover classes caused by spatial and temporal domain discrepancies in cross-domain hyperspectral image classification, this paper proposes BiDA, a bidirectional domain adaptation framework. BiDA employs a three-branch Transformer architecture integrated with a semantic tokenizer and introduces Coupled Multi-head Cross-Attention (CMCA) to enable bidirectional feature interaction between source and target domains. Furthermore, it incorporates a bidirectional distillation loss and an Adaptive Regularization Strategy (ARS) to jointly enhance domain-invariant feature representation and robustness against spectral noise. Evaluated on multiple cross-temporal and cross-scene airborne and satellite hyperspectral datasets, BiDA consistently outperforms state-of-the-art methods, achieving average accuracy improvements of 3–5% in tree species classification. These results demonstrate BiDA’s effectiveness, generalizability, and practical applicability for real-world cross-domain hyperspectral classification tasks.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Multi-modal Vision
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Utilizing hyperspectral remote sensing technology enables the extraction of fine-grained land cover classes. Typically, satellite or airborne images used for training and testing are acquired from different regions or times, where the same class has significant spectral shifts in different scenes. In this paper, we propose a Bi-directional Domain Adaptation (BiDA) framework for cross-domain hyperspectral image (HSI) classification, which focuses on extracting both domain-invariant features and domain-specific information in the independent adaptive space, thereby enhancing the adaptability and separability to the target scene. In the proposed BiDA, a triple-branch transformer architecture (the source branch, target branch, and coupled branch) with semantic tokenizer is designed as the backbone. Specifically, the source branch and target branch independently learn the adaptive space of source and target domains, a Coupled Multi-head Cross-attention (CMCA) mechanism is developed in coupled branch for feature interaction and inter-domain correlation mining. Furthermore, a bi-directional distillation loss is designed to guide adaptive space learning using inter-domain correlation. Finally, we propose an Adaptive Reinforcement Strategy (ARS) to encourage the model to focus on specific generalized feature extraction within both source and target scenes in noise condition. Experimental results on cross-temporal/scene airborne and satellite datasets demonstrate that the proposed BiDA performs significantly better than some state-of-the-art domain adaptation approaches. In the cross-temporal tree species classification task, the proposed BiDA is more than 3%$sim$5% higher than the most advanced method. The codes will be available from the website: https://github.com/YuxiangZhang-BIT/IEEE_TCSVT_BiDA.

Problem

• Address spectral shifts in cross-domain hyperspectral image classification
• Enhance adaptability and separability via bi-directional domain adaptation
• Improve feature extraction in noisy conditions for target scenes

Innovation

• Bi-directional Domain Adaptation for HSI classification
• Triple-branch transformer with semantic tokenizer
• Coupled Multi-head Cross-attention mechanism