Search Results (42)

Cross-scene hyperspectral image (HSI) classification seeks to learn a classifier from annotated source-scene data and deploy it on unlabeled scenes whose imaging conditions and data distributions differ from those seen during training. Existing cross-scene learning strategies mainly include domain adaptation (DA) and domain generalization (DG). In practical scenarios, target-domain samples are commonly unknown, inaccessible, or time-varying before deployment. DG is a more practical choice for such applications. Yet, single-source DG still faces a key difficulty: expanded samples must contain meaningful domain changes without corrupting class semantics. If the generated domains are weak or deviate from their original categories, the classifier may learn unstable or misleading cues. Therefore, we introduce the View-Consistent Domain Calibration Network (VDCnet), which is designed to improve the quality and training value of generated samples for single-source cross-scene classification. VDCnet consists of a Calibrated Expansion Generator (CEG) and a View Semantic Matching Mechanism (VSM). CEG performs reliability-gated spectral-spatial residual perturbation to produce semantically trustworthy extended samples, rather than simply enlarging the sample set. VSM further enforces multi-view semantic consistency in both prediction distributions and projected feature representations, promoting diverse feature learning while suppressing semantic drift. Experiments on the Houston, Pavia, and Shanghai–Hangzhou datasets demonstrate that VDCnet improves overall accuracy over the leading DG methods by 1.29, 2.65, and 1.26 percentage points, respectively, indicating its superior performance. Full article

Knowledge transfer plays a crucial role in cross-scene hyperspectral imaging (HSI). However, existing studies often overlook the challenges of gradient conflicts and dominant gradients that arise during the optimization of shared parameters. Moreover, many current approaches fail to simultaneously capture both agreement and disagreement information, relying only on a limited shared subset of target features and consequently missing the rich, diverse patterns present in the target scene. To address these issues, we propose an Agreement–Disagreement Guided Knowledge Transfer (ADGKT) framework that jointly models optimization consistency and representation diversity for heterogeneous cross-scene HSI classification. The proposed framework consists of two complementary mechanisms. The agreement mechanism stabilizes joint optimization by mitigating gradient conflicts and balancing the contributions of source and target domains during shared parameter learning. The disagreement mechanism explicitly preserves complementary target-specific representations through a dedicated disagreement branch and integrates transferable and target-critical information into a unified predictor. Unlike conventional transfer learning approaches that rely solely on feature alignment, the proposed framework simultaneously encourages transferable knowledge sharing and target-specific representation learning, thereby improving robustness under heterogeneous scene discrepancies. Extensive experiments demonstrate the effectiveness and superiority of the proposed method in achieving robust and balanced knowledge transfer across heterogeneous HSI scenes. Full article

Hyperspectral sensors provide high-dimensional spectral–spatial observations for land-cover analysis, but reliable classification remains difficult when only a few target-scene labels are available. Cross-domain few-shot hyperspectral image classification usually depends on sparse support samples, so final decisions can be unstable in low-margin regions where repairable errors and correctly classified long-tail samples are entangled. We propose Boundary-Risk Graph Calibration (BRGC), a risk-controlled calibration framework that improves support-set decision reliability. BRGC combines boundary-aware mixability training with inference-time graph residual calibration. During inference, support labels are clamped, an unlabeled target-query graph provides structural smoothing evidence, and the original classification scores are modified only through low-margin gating and bounded residual updates. On 10 target datasets with 10 random seeds, BRGC consistently improves its base classifier and achieves the highest macro-average OA, AA, and Kappa among matched-protocol transductive baselines. Repair/damage diagnostics, ablation studies, parameter sensitivity analysis, and cross-method adaptation show that BRGC improves scarce-label hyperspectral image interpretation by converting query-graph structure into low-intervention reliability evidence. Full article

Hyperspectral imaging (HSI) is a state-of-the-art analytical technique that combines the use of conventional digital imaging and spectroscopy to capture both spatial and spectral information simultaneously in hundreds of narrow, adjacent wavelength bands. In recent decades, the progress in HSI has been rapid, and the technique has been increasingly utilized in forensic sciences, demonstrating its superiority to standard analytical techniques with respect to being non-invasive and contact-free. Although numerous forensic HSI articles have appeared in the literature in recent years, there has yet to emerge a systematic comparison of HSI performance, instrumentation, and cross-domain translational difficulties within forensic science. This review fills this important gap by analyzing the principles, instrumentations, methods of HSI data processing, and potential applications of HSI in forensics in the context of nine important fields: blood stain analysis and estimation of blood age; document authentication; fingerprint detection and enhancement; gunshot residue (GSR) analysis; analysis of trace evidences; detection of biological fluids; postmortem interval (PMI) estimation; determination of bruise age; and multidisciplinary applications. Comparative analysis of over fifty peer-reviewed articles published from 2010 to 2026 in HSI-based forensic sciences is provided herein, with classification accuracies between 81% and 100%. The use of chemometric and machine-learning methods, such as principal component analysis (PCA), support vector machines (SVM), partial least square discriminant analysis (PLS-DA), and Convolutional Neural Networks (CNNs), is carefully analyzed. Some problems concerning standardization, legal acceptance, data sets available, and forensic application are considered alongside future developments of HSI technology. Full article

Cross-scene classification of hyperspectral images attracts extensive research attention due to the prominent distribution discrepancies existing in hyperspectral images across different scenes. Most existing methods mitigate domain shift by expanding source domain samples and aligning feature distributions. However, these approaches fail to fully explore the spatial semantics of samples during the expansion process. Moreover, features are compressed into one-dimensional vectors in the alignment stage, resulting in the loss of critical spatial location information. To address the above issues, this paper proposes a multi-scale semantic selection and spatial constraint-guided network (MSCGnet). Specifically, the multi-scale semantic selection generator adopts a spatial diffusion scanning strategy to optimize the token serialization rule of Mamba. Pixels are arranged from the center to the periphery to maintain spatial continuity. Combined with the multi-scale semantic selection routing, multi-scale spectral–spatial features are extracted and a semantic selection matrix is constructed to guide Mamba to generate diverse augmented samples. The spatial constraint-guided discriminator leverages class activation map projection to impose explicit spatial constraints on feature distributions, further improving the reliability of augmented samples. Comprehensive experiments on multiple cross-scene HSI datasets demonstrate that the proposed method achieves superior classification accuracy and generalization performance with low model complexity. Full article

Accurate hyperspectral image analysis plays a critical role in environmental monitoring, precision agriculture, and urban mapping, yet acquiring large-scale annotated datasets for newly emerging scenes and sensors remains challenging. Cross-domain few-shot hyperspectral image classification addresses this bottleneck by transferring knowledge from a labeled source domain to a sparsely annotated target domain. Existing prototype-based approaches commonly use a single-mean prototype per class, which is often inadequate for target classes with spectral–spatial heterogeneity, intra-class dispersion, and unstable episode-level statistics. Consequently, the resulting alignment reference may fail to accurately characterize class structure, thereby exacerbating negative transfer under domain shift. To address this issue, we propose a plug-and-play prototype-stability module that combines Uncertainty-Guided Clustered Alignment (UGCA) with Center Regularization. UGCA identifies hard classes using a class-level dispersion proxy and dynamically constructs multi-center prototypes to better capture intra-class heterogeneity beyond the single-mean assumption. Meanwhile, Center Regularization adds a lightweight compactness constraint on query embeddings to reduce prototype drift under sparse supervision. Experiments on three cross-domain tasks demonstrate the effectiveness of the proposed method. Compared with the reproduced MLPA baseline over 10 independent runs, the proposed method improves the mean OA from 69.21 ± 2.71%, 81.90 ± 3.45%, and 76.92 ± 1.10% to 71.24 ± 3.39%, 83.73 ± 3.89%, and 78.24 ± 1.55% on the Indian Pines (IP), University of Pavia (UP), and Houston (HT) target domains, respectively. Furthermore, cross-framework insertion into Gia-CFSL further verifies that the module is host-agnostic across prototype-driven CD-FSL frameworks and improves prototype-based hyperspectral image analysis without changing the inference pipeline. These results indicate that improving prototype quality is a critical and complementary dimension for robust cross-domain few-shot hyperspectral classification under sparse supervision. Full article

Cross-scene Hyperspectral Image (HSI) classification faces substantial domain shifts caused by sensor heterogeneity, acquisition variation, and scene diversity. While benchmark annotations are assigned to individual center pixels, local patches often contain implicit multi-label semantics due to spectral mixing and spatial overlap. This mismatch distorts prediction structure, exacerbates generalization errors, and limits the effectiveness of standard domain generalization (DG) techniques focused solely on feature or prediction invariance. We propose Class-Aware Semantic Calibration (CASC), a systematic semantic structure calibration framework that addresses three complementary distortions induced by mismatched patch supervision: (i) Balance corrects class frequency bias via reweighted supervision; (ii) Separability enhances boundary decision stability through margin-based logit calibration; and (iii) Independence reduces domain-specific spurious co-occurrence via prediction covariance decorrelation. To preserve calibrated semantics under pseudo-source shift, we further introduce a complementary DualAlign (DA) module, which jointly aligns feature statistics and prediction distributions, enforcing consistency at both representation and semantic levels. Extensive experiments on three cross-scene benchmarks (Houston, Pavia, and WHU-Hi) demonstrate that CASC-DA consistently improves performance over strong baselines, achieving an average gain of 3.0% in overall accuracy and 4.9% in Kappa coefficient compared with the best-performing baseline on each dataset. These results underscore the importance of semantic structure calibration for domain-generalized HSI classification. Full article

Joint classification of hyperspectral images (HSI) and light detection and ranging (LiDAR) data is important for land-cover recognition, as it can exploit both spectral discrimination and structural elevation information. However, existing methods mainly focus on visual feature fusion and insufficiently utilize class-level semantic priors, which limits their discriminative capability in complex boundaries, visually similar categories, and limited-sample scenarios. To address these issues, this paper proposes a text-guided multimodal semantic fusion network for HSI–LiDAR classification. Specifically, a Channel-Modulated Mobile Convolution Module (CMMC) is designed to extract modality-specific features, a Spatial–Frequency Feature Enhancement Module (SFFE) is introduced to enhance spatial-boundary and frequency-domain structural representations, and a Bidirectional Cross-Modal Fusion Module (BCMF) is developed to promote complementary interaction between spectral and structural information. Meanwhile, class-level textual descriptions are constructed from class names, color attributes, and geographical contexts, and a text encoder is employed to obtain semantic prototypes. Furthermore, a multi-branch vision–text semantic alignment mechanism projects HSI features, LiDAR features, and fused features into a shared semantic space for joint constraints, improving semantic consistency and class separability. Experiments on the Houston2013, Augsburg, and Trento datasets demonstrate the effectiveness of the proposed method. It achieves an overall accuracy of 98.76% on Houston2013, with improvements of 0.62%, 0.52%, and 0.67 in overall accuracy, average accuracy, and Kappa coefficient × 100 over the best competing results, respectively. The proposed method also obtains the best overall metrics on Augsburg and Trento, and ablation studies verify the effectiveness of the proposed components. Full article

Hyperspectral (HS) imaging has proven to be a promising intraoperative tool for tissue discrimination. However, obtaining representative datasets for intraoperative imaging remains challenging due to the complexity of surgical workflows and the sensitivity of the operating environments. Hence, developing new methods for cross-system feature adaptation could address this limitation. This work proposes a method for mapping high-resolution spectral data into lower-resolution sensor-conditioned domains, generating synthetic HS data that replicate the spectral features of the target system. We assessed the mapped data using public HS datasets and quantified spectral similarities using different metrics. Additionally, we evaluated the method with a HS classification framework for an intraoperative brain tumour classification problem. Results demonstrate that the synthetic data achieve high spectral alignment to original and actual data, captured with the target system. The brain tumour classification results show comparable performance between data modalities. Overall, this work provides a way to adapt existing HS datasets to complement newly acquired data, accelerating the development of artificial intelligence algorithms. This is particularly relevant in medical research, and especially in neurosurgery, where the complexity of acquisition environments limits the collection of large datasets. Full article

Cross-domain few-shot hyperspectral image (HSI) classification is challenging due to limited labeled samples and distribution shifts across sensors and acquisition scenes, which often degrade feature representation and classification performance. This study proposes a lightweight hierarchical CNN–Transformer framework, termed LGDAF-Net (Lightweight Global and Local Dual Attention Fusion Network), for effective cross-domain few-shot HSI classification. The framework progressively enhances spectral–spatial representation through three stages: spectral–spatial feature recalibration, local spatial structure perception, and global contextual modeling. Specifically, a spectral–spatial dual-attention enhancement module (SESA) is introduced to emphasize informative spectral responses and suppress redundancy. A Local Attention Spatial Perception Module (LASPM) is designed to capture fine-grained spatial structures, while a lightweight Transformer-based Global Attention Context Modeling Module (GACM) models long-range spatial dependencies. In addition, kernel triplet loss and domain adversarial learning are incorporated to improve feature discrimination and promote cross-domain feature alignment. Experimental results on three benchmark datasets demonstrate that the proposed method achieves competitive performance compared with existing methods. Full article

Deep-learning-based methods have achieved remarkable success in hyperspectral image (HSI) classification tasks due to their promising ability. However, the high dimensionality and spectral–spatial correlations of HSIs usually lead to information redundancy and feature entanglement, limiting the classification performance. To address these issues, we propose a novel high–low frequency interaction Mamba network, called HL-Mamba, which achieves effective decoupling and interaction between global structures and edge details of HSIs in the frequency domain, thereby improving spectral–spatial representation for HSI classification. Specifically, a high–low frequency decomposition Mamba module is designed to decompose the HSI into low-frequency structural and high-frequency edge detail components, which allows the model to learn global structures and fine-grained details, enhancing classification performance. By employing two parallel Mamba branches to model long-range dependencies across different frequency components, the network achieves efficient global modeling while mitigating information redundancy. Furthermore, a cross-frequency interaction module is designed to establish complementary information flow between high- and low-frequency features through a dynamic attention mechanism. In this way, low-frequency structural features guide the aggregation of high-frequency details, whereas high-frequency textures refine global structural representations, yielding more discriminative spectral–spatial features for HSI classification. In addition, a frequency alignment loss is designed to enhance the consistency and complementarity between high- and low-frequency features, further improving classification performance. Extensive experiments on four public benchmark datasets (i.e., Indian Pines, Pavia University, WHU-Hi-HanChuan, and Houston datasets) demonstrate that the proposed HL-Mamba significantly outperforms eight comparison methods, achieving an overall accuracy of 94.07%, 93.82%, 95.28%, and 87.32%, respectively. Ablation studies further verify the effectiveness of core component within the network. Full article

With the increasing availability of satellite imagery and the shortening revisit intervals, efficiently processing satellite hyperspectral images has become a critical task. However, in practice, a large portion of satellite hyperspectral data remains unlabeled, making it difficult to achieve satisfactory classification performance using satellite data alone. Meanwhile, UAV-based platforms offer acquisition flexibility, which facilitates the collection of rich and detailed information. To address these challenges, this paper proposes a method called Sharpness-Aware Minimization with Local-to-Global Feature Enhancement (SAMLFE), which uses UAV hyperspectral images for training to enhance the fine-grained classification performance of satellite hyperspectral images in large scenes. Specifically, a spectral dimension mapping model is first employed to unify UAV and satellite images into a common spectral dimension, thereby mitigating the impact of inconsistent feature representations. Next, a local-to-global feature extraction network is constructed to capture both local details and global semantics. Few-shot learning is applied to extract discriminative features from both the source and target domains within the shared feature space, thereby enhancing the model’s ability to utilize limited labeled data efficiently. Furthermore, a conditional adversarial domain adaptation strategy is adopted to align the feature distributions of the source and target domains, thereby alleviating spectral shift. Meanwhile, the integration of an improved Sharpness-Aware Minimization (ISAM) enhances the model’s robustness across domains. Finally, the K-Nearest Neighbor algorithm is employed to perform accurate classification. Experimental results on multiple datasets demonstrate that the proposed method achieves superior generalization and classification performance in cross-domain hyperspectral image classification. It also outperforms existing methods in terms of feature distribution alignment, robustness of feature extraction, and adaptability to small-sample scenarios. Full article

Cross-scene hyperspectral image (HSI) classification under single-source domain generalization (DG) is a crucial yet challenging task in remote sensing. The core difficulty lies in generalizing from a limited source domain to unseen target scenes. We formalize this through the causal theory, where different sensing scenes are viewed as distinct interventions on a shared physical system. This perspective reveals two fundamental obstacles: interventional distribution shifts arising from varying acquisition conditions, and confounding biases induced by spurious correlations driven by domain-specific factors. Taking the above considerations into account, we propose CauseHSI, a causality-inspired framework that offers new insights into cross-scene HSI classification. CauseHSI consists of two key components: a Counterfactual Generation Module (CGM) that perturbs domain-specific factors to generate diverse counterfactual variants, simulating cross-domain interventions while preserving semantic consistency, and a Causal Disentanglement Module (CDM) that separates invariant causal semantics from spurious correlations through structured constraints under a structural causal model, ultimately guiding the model to focus on domain-invariant and generalizable representations. By aligning model learning with causal principles, CauseHSI enhances robustness against domain shifts. Extensive experiments on the Pavia, Houston, and HyRANK datasets demonstrate that CauseHSI outperforms existing DG methods. Full article

Hyperspectral image (HSI) classification is pivotal for remote sensing applications, including environmental monitoring, precision agriculture, and urban land-use analysis. However, its accuracy is often limited by scarce labeled data, class imbalance, and domain discrepancies between standard RGB and HSI imagery. Although recent deep learning approaches, such as 3D convolutional neural networks (3D-CNNs), transformers, and generative adversarial networks (GANs), show promise, they struggle with spectral fidelity, computational efficiency, and cross-domain adaptation in label-scarce scenarios. To address these challenges, we propose the Transformer–Graph Convolutional Network–Diffusion with Hybrid Domain Adaptation (TGDHTL) framework. This framework integrates domain-adaptive alignment of RGB and HSI data, efficient synthetic data generation, and multi-scale spectral–spatial modeling. Specifically, a lightweight transformer, guided by Maximum Mean Discrepancy (MMD) loss, aligns feature distributions across domains. A class-conditional diffusion model generates high-quality samples for underrepresented classes in only 15 inference steps, reducing labeled data needs by approximately 25% and computational costs by up to 80% compared to traditional 1000-step diffusion models. Additionally, a Multi-Scale Stripe Attention (MSSA) mechanism, combined with a Graph Convolutional Network (GCN), enhances pixel-level spatial coherence. Evaluated on six benchmark datasets including HJ-1A and WHU-OHS, TGDHTL consistently achieves high overall accuracy (e.g., 97.89% on University of Pavia) with just 11.9 GFLOPs, surpassing state-of-the-art methods. This framework provides a scalable, data-efficient solution for HSI classification under domain shifts and resource constraints. Full article

A major computational bottleneck in classifying large-scale hyperspectral images (HSI) is the mandatory data decompression prior to processing. Compressed-domain computing offers a solution by enabling deep learning on partially compressed data. However, existing compressed-domain methods are predominantly tailored for the Discrete Cosine Transform (DCT) used in natural images, while HSIs are typically compressed using the Discrete Wavelet Transform (DWT). The fundamental structural mismatch between the block-based DCT and the hierarchical DWT sub-bands presents two core challenges: how to extract features from multiple wavelet sub-bands, and how to fuse these features effectively? To address these issues, we propose a novel framework that extracts and fuses features from different DWT sub-bands directly. We design a multi-branch feature extractor with sub-band feature alignment loss that processes functionally different sub-bands in parallel, preserving the independence of each frequency feature. We then employ a sub-band cross-attention mechanism that inverts the typical attention paradigm by using the sparse, high-frequency detail sub-bands as queries to adaptively select and enhance salient features from the dense, information-rich low-frequency sub-bands. This enables a targeted fusion of global context and fine-grained structural information without data reconstruction. Experiments on three benchmark datasets demonstrate that our method achieves classification accuracy comparable to state-of-the-art spatial-domain approaches while eliminating at least 56% of the decompression overhead. Full article