Hyperspectral imaging (HSI) captures abundant spectral information of land covers while light detection and ranging (LiDAR) provides elevation and structural characteristics. Joint classification of HSI and LiDAR data can effectively merge spectral and elevation information to enhance the outcome of land cover classification. Current HSI and LiDAR joint classification approaches mainly employ a three-layer deep network to extract high-order features, followed by a concatenation or weighted fusion scheme which cannot fully exploit the unique properties of different data modalities. Meanwhile, these methods usually require high computational resources. To alleviate these issues, this paper proposes a masked self-attention fusion network (MSAF) for joint HSI and LiDAR classification, where a cascaded cross-attention fusion framework is designed to fully merge different stages of features. First, a mobile convolution block is developed to extract multi-modal data features. Then, a multi-view sequence embedding method is proposed to effectively integrate elevation information and spectral-spatial information so as to obtain token sequences. Finally, an effective masked self-attention mechanism is designed to fuse token sequences. Experimental results on multiple datasets indicate that the proposed framework significantly outperforms other advanced multi-modal fusion methods in terms of classification performance and computing efficiency. The code of this manuscript is available on https://github.com/lulushh/MSAF.

3D point cloud classification is an important task in autonomous driving for capturing the characteristics of a 2D manifold embedded in a 3D ambient space. Despite their excellent performance, existing 3D point cloud classifiers have been shown to be as vulnerable to adversarial examples as 2D models. However, current attack methods struggle to achieve a balance between adversarial effectiveness and imperceptibility, often resulting in either low attack success rates or significant outliers that are easily removed by statistical outlier removal. In this paper, we develop a ranking map to evaluate the representational capacity of the model for individual points and launch attacks by grouping key points into a critical point set. To ensure invariance to point cloud transformations, we propose a combined search-direction method instead of randomly selecting attack directions, thereby enhancing the robustness of the generated adversarial examples in the physical world. Additionally, we introduce a surrogate test target structure to improve the attack strength of adversarial point clouds. To enhance naturalness, we develop an adaptive multi-directional perturbation attack algorithm called HAMC (Hybrid Attacks with Multiple Constraints), in which different attack directions exhibit varying degrees of sensitivity to curvature. Experiments on typical point cloud classification models demonstrate that our method significantly improves the attack success rate and achieves a better balance between adversarial potency and invisibility compared to state-of-the-art attack methods.

Hyperspectral image (HSI) classification is commonly influenced by convolution neural networks (CNNs). However, the large number of parameters and computational complexity associated with CNNs can limit their practical application, particularly when computing and storage resources are limited. To address this challenge, we propose a channel-layer-oriented lightweight network for HSI classification. Motivated by existing structures that typically set large channels and stack multiple layers, we give more optimal solutions strategically to further compress the model. For intralayer feature extraction, we develop a channel-oriented spectral–spatial module (COS2M), which introduces a dual-single-channel (DSC) 3-D convolution that works in conjunction with depthwise convolution to fully extract spectral–spatial information. For interlayer information transmission, we propose a novel neighbor-pixel-aware activation function (NPAF), where the activation of a single pixel is determined by the learnable interaction with its neighbor range that enhances information transmission and improves the network’s fitting ability through the single activation layer. By implementing these strategies, we aim to overcome the limitations of traditional CNNs and enable efficient HSI classification within resource-constrained environments. The whole network is designed to be a compact end-to-end structure. It achieves better classification performance than other deep learning methods and lightweight models, even with limited training samples. The network parameters, model complexity, and inference time also demonstrate significant superiority, as confirmed by experiments on three benchmark datasets. The source codes are available publicly at:https://github.com/AchunLee/CLOLN_TGRS

In hyperspectral image classification, using spatial information as a supplement to spectral information is an effective way to improve classification accuracy. In this paper, a novel robust complementary method using spectral–spatial information is proposed to reduce the information loss in feature extraction, thus improving the classification effect. In short, two complementary feature extraction stages are used to get the probability maps for decision fusion. In the stage of pre-processing feature extraction, we propose an adaptive cubic total variational smoothing method (ACTVSP), which is first proposed and applied in the remote sensing research field, to obtain the first-stage probability map. At the same time, we utilize edge-preserving filtering in the post-processing stage and obtain the second probability map by the means of pixel-level classifier. Finally, the probability-like maps obtained in the above two stages are integrated by decision fusion rules. Experiments on ten public data sets show that the effectiveness of our proposed method and demonstrate the superior of distinguishing different land covers on the basis of very few training samples. Therefore, it can be applied to practical applications in different scenes.

In practical hyperspectral image cross-scene classification (HSICC) tasks, the arduous work of obtaining labels and the distribution inconsistency caused by spectral shift leave deep learning methods to face great challenges. Unsupervised domain adaptation aims to exploit knowledge from the annotated source domain and transfer it to the unlabeled target domain, thereby boosting the performance of unsupervised classification. Nevertheless, existing HSICC approaches cannot effectively exploit class structure information from target data. Specially, this article proposes an unsupervised joint adversarial domain adaptation (UJADA) architecture for HSICC to further narrow the distribution gap between distinct domains. The proposed method contains two modules: domain adversarial module that learns domain-invariant features, bi-classifier adversarial module that explores task-specific decision boundaries between classes, and both share a feature generator consisting of the dense-based spectral-spatial convolution network. The UJADA simultaneously considers domain-level and class-level feature alignment between source and target hyperspectral images in a unified adversarial learning processing. Furthermore, the classifier determinacy disparity metric is introduced to fine-grained measure the output probabilistic discrepancy between two task-specific label predictors on target data, thus ensuring the discriminability of transferable features. Comprehensive experiments and ablation studies conducted on two public cross-scene data pairs and our newly acquired ultra-low-altitude hyperspectral images under different illumination conditions demonstrate the superior performance of the proposed algorithm, which will greatly promote the practical application of hyperspectral intelligent perception technology.