Hyperspectral image (HSI) classification holds significant application value in precision agriculture, environmental monitoring, and other fields. However, the high cost of large-scale labeling limits the widespread application of deep learning methods. Utilizing a large amount of labeled HSI data for auxiliary training of cross-domain few-shot learning (FSL) methods is an effective means to address this issue. Yet, in practical applications, spectral and spatial features vary across different scenarios, posing significant challenges to the generalizability and accuracy of cross-domain learning models. To tackle this problem, this article proposes a multilevel prototype alignment (MLPA) method for cross-domain few-shot classification, which adjusts feature representations by implementing multilevel feature alignment strategies at various hierarchical levels of the feature extraction network. This approach achieves fine-grained alignment of the source and target domain feature distributions, effectively reducing domain shift and enhancing the model’s generalization capability on target domain data. Furthermore, by employing class prototype-based domain adversarial training, the method aligns the prototypes of the source and target domains without simply aligning the entire feature space, thus avoiding overlap in the feature distribution of different classes within the domain and mitigating negative transfer. The MLPA method effectively enhances the generalizability and discriminative power of features in the target domain, thereby improving the performance of cross-domain HSI classification. Experimental results demonstrate that MLPA outperforms other cross-domain few-shot HSI classification methods. Our source code is available athttps://github.com/hejinrong/MLPA.

Prototypical network-based few-shot learning (FSL) has demonstrated promising performance for hyperspectral image (HSI) classification tasks under scarce sample conditions. However, existing prototype-based FSL methods suffer from data distribution variations among randomly sampled tasks, leading to unstable class prototype representations and weak cross-task generalization with limited samples. To address this issue, we propose a momentum-enhanced dual-prototype learning (MEDPL) framework for robust few-shot HSI classification. Firstly, a momentum-updated prototype mechanism constructs an iteratively optimized prototype memory bank. It obtains accumulated prototypes by exponentially decaying weighted fusion of historical and current prototypes, significantly suppressing noise from randomly sampled data and class center shifts caused by distribution bias. Simultaneously, a class-conditioned perturbation-augmentation strategy is introduced. It generates adaptive noise perturbations for support set features based on learnable covariance matrices to obtain enhanced prototypes, thereby improving the generalization representation capability of class prototypes across tasks. Secondly, a dual-prototype metric learning framework is designed, jointly utilizing accumulated prototypes and enhanced prototypes to synergistically enhance the model’s classification stability and cross-task generalization, thus significantly improving the robustness of few-shot classification. Experimental results demonstrate that MEDPL outperforms other few-shot hyperspectral image classification methods. Our source code is available at https://github.com/hejinrong/MEDPL.

Ground-penetrating radar (GPR) with different center frequencies can detect defects at different depths with a range of resolutions enabling it to be used for subsurface defect inspection. However, the existing deep learning methods cannot accurately invert the permittivity from GPR data of different frequencies, due to the limited number of labeled GPR images for every center frequency. To tackle this challenge, a semi-supervised deep neural network-based cross-frequency GPR data inversion method was proposed, which enables the generalized model to be trained on the GPR data with one frequency (source domain) for migration to other frequencies (target domain). The method was trained in a semi-supervised manner using a small number of paired GPR data with permittivity labels and a large amount of unlabeled GPR data without corresponding permittivity maps. An adversarial learning mechanism together with a novel random perturbation strategy was designed to improve the global inversion performance for a large-scale structure and avoid a discontinuity in the reconstructed shapes. Furthermore, a mean teacher architecture is introduced to improve the inversion accuracy of detailed information from the unlabeled GPR data under different perturbation conditions. The ablation and comparative experiments results indicated that the proposed method outperforms other methods and can be effectively generalized to GPR B-Scan data with different frequencies and signal-to-noise ratios. In addition, sandbox model testing was conducted and the results indicate that this method can transfer the knowledge from the synthetic data domain to the real data domain with satisfactory results.

Ground penetrating radar (GPR) enables infrastructure inspection using consecutive and long survey lines. However, the existing GPR data processing methods may lead to distortions or dislocations in the reconstructed shapes of the detected objects or even inconsistencies of the inverted dielectric values when performing inversion or object identification directly using GPR data obtained from the consecutive and long survey lines. To overcome these issues, this study proposed a novel deep neural network (DNN) architecture named GPRI2Net to simultaneously reconstruct the permittivity maps and categorize the object class labels from the GPR data of consecutive and long survey lines. GPRI2Net combined a convolutional neural network (CNN) based on DenseUnet and a recurrent neural network (RNN) based on bidirectional convolutional long short-term memory (Bi-ConvLSTM) to exploit the contextual information in and between the B-Scan segments extracted from the GPR data of a consecutive and long survey line. In addition, GPRI2Net performed inversion and object identification simultaneously using one network, which highly shared features between the two tasks and greatly reduced the computational complexity. Validation experiments were performed at two levels: first, using synthetic data based on the tunnel liner defects model and then using a sandbox model test in a realistic scenario. The results demonstrated that GPRI2Net can reconstruct consecutive permittivity maps and categorize the object class labels from GPR data with different dominant frequencies and survey line lengths and achieved a superior performance using the synthetic data compared to several other methods. Moreover, GPRI2Net also achieved satisfactory results using real-world GPR data.

A DNN architecture referred to as GPRInvNet was proposed to tackle the challenges of mapping the ground-penetrating radar (GPR) B-Scan data to complex permittivity maps of subsurface structures. The GPRInvNet consisted of a trace-to-trace encoder and a decoder. It was specially designed to take into account the characteristics of GPR inversion when faced with complex GPR B-Scan data, as well as addressing the spatial alignment issues between time-series B-Scan data and spatial permittivity maps. It displayed the ability to fuse features from several adjacent traces on the B-Scan data to enhance each trace, and then further condense the features of each trace separately. As a result, the sensitive zones on the permittivity maps spatially aligned to the enhanced trace could be reconstructed accurately. The GPRInvNet has been utilized to reconstruct the permittivity map of tunnel linings. A diverse range of dielectric models of tunnel linings containing complex defects has been reconstructed using GPRInvNet. The results have demonstrated that the GPRInvNet is capable of effectively reconstructing complex tunnel lining defects with clear boundaries. Comparative results with existing baseline methods also demonstrated the superiority of the GPRInvNet. For the purpose of generalizing the GPRInvNet to real GPR data, some background noise patches recorded from practical model testing were integrated into the synthetic GPR data to retrain the GPRInvNet. The model testing has been conducted for validation, and experimental results revealed that the GPRInvNet had also achieved satisfactory results with regard to the real data.