SpectralAdapt: Semi-Supervised Domain Adaptation with Spectral Priors for Human-Centered Hyperspectral Image Reconstruction

2025-11-17

AI Summary

Medical hyperspectral imaging suffers from scarce human subject data and severe domain shift, limiting reconstruction performance. To address this, we propose a semi-supervised domain adaptation (SSDA) framework for high-fidelity RGB-to-hyperspectral image reconstruction. Our method introduces two key innovations: (1) Spectral Density Masking—a self-adaptive masking strategy applied to RGB channels to enhance spectral reasoning; and (2) Spectral Endmember Representation Alignment, which leverages physically interpretable endmembers as domain-invariant anchors to improve accuracy and stability of predictions on unlabeled samples. The framework jointly optimizes model parameters via consistency regularization, momentum-based teacher–student updating, and spectral prior modeling, effectively exploiting limited labeled and abundant unlabeled data. Experiments on multiple benchmark datasets demonstrate significant improvements in spectral fidelity (e.g., +2.1 dB PSNR) and cross-domain generalization, alongside enhanced training stability—establishing a novel paradigm toward practical deployment of medical hyperspectral imaging.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Multi-modal Vision
• Application Domains: Humanities & Computational Social Science

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health

Abstract

Hyperspectral imaging (HSI) holds great potential for healthcare due to its rich spectral information. However, acquiring HSI data remains costly and technically demanding. Hyperspectral image reconstruction offers a practical solution by recovering HSI data from accessible modalities, such as RGB. While general domain datasets are abundant, the scarcity of human HSI data limits progress in medical applications. To tackle this, we propose SpectralAdapt, a semi-supervised domain adaptation (SSDA) framework that bridges the domain gap between general and human-centered HSI datasets. To fully exploit limited labels and abundant unlabeled data, we enhance spectral reasoning by introducing Spectral Density Masking (SDM), which adaptively masks RGB channels based on their spectral complexity, encouraging recovery of informative regions from complementary cues during consistency training. Furthermore, we introduce Spectral Endmember Representation Alignment (SERA), which derives physically interpretable endmembers from valuable labeled pixels and employs them as domain-invariant anchors to guide unlabeled predictions, with momentum updates ensuring adaptability and stability. These components are seamlessly integrated into SpectralAdapt, a spectral prior-guided framework that effectively mitigates domain shift, spectral degradation, and data scarcity in HSI reconstruction. Experiments on benchmark datasets demonstrate consistent improvements in spectral fidelity, cross-domain generalization, and training stability, highlighting the promise of SSDA as an efficient solution for hyperspectral imaging in healthcare.

Problem

• Bridging domain gap between general and human-centered hyperspectral imaging datasets
• Addressing spectral degradation and data scarcity in HSI reconstruction
• Recovering hyperspectral data from RGB with limited human HSI labels

Innovation

• Semi-supervised domain adaptation bridges general and human-centered datasets
• Spectral Density Masking adaptively masks RGB channels by complexity
• Spectral Endmember Representation Alignment uses domain-invariant anchors for guidance