Deep learning-based methods based on Convolutional Neural Networks (CNNs) have demonstrated remarkable performance in hyperspectral image (HSI) classification. Most of these approaches are only based on 2-D CNN or 3-D CNN. It is dramatic from the literature that using just 2-D CNN may result in missing channel relationship information and using just 3-D CNN may make the model very complex. Moreover, the existing network models do not pay enough attention to extracting spectral-spatial correlation information. To address these issues, we propose a deep collaborative attention network for HSI classification by combining 2-D CNN and 3-D CNN (CACNN). Specifically, we first extract spectral-spatial features by using 2-D CNN and 3-D CNN, respectively, and then use a "NonLocalBlock" to combine these two kinds of features. This block serves as a typical spatial attention mechanism and makes salient features be emphasized. Then, we propose a "Conv Block" that is similar to the lightweight dense block to extract correlation information contained in the feature maps. Finally, we consider a deep multilayer feature fusion strategy, and thereby combine the features of different hierarchical layers to extract the strong correlated spectral-spatial information among them. To test the performance of CACNN approach, several experiments are performed on four well-known hyperspectral images. The results are compared with the state-of-the-art approaches and satisfactory performance is obtained by our proposed method.

Significant progress has been achieved in remote sensing image scene classification (RSISC) with the development of convolutional neural networks (CNNs) and vision transformers (ViT). However, high intra-class diversity and inter-class similarity are still enormous challenges for RSISC. Metric learning can effectively improve the discriminative ability of deep representations by constraining the distance between features. Previous metric learning methods only optimize the feature space representation through metric function, ignoring the information interaction between samples. For complex scene images, similarity and discriminative knowledge need to be summarized from the multiple positive and negative pairs. We propose a novel efficient multi-sample contrastive network (EMSCNet) to integrate knowledge from multiple samples. Specifically, we construct a dynamic dictionary with momentum updates to mine positive and negative pairs from the entire dataset. Then, the similarity and discriminative knowledge between samples are summarized by introducing a contrastive module. Finally, the knowledge of the contrastive module is transferred to the backbone classifier through knowledge distillation. The proposed contrastive module can be easily embedded into the training process of CNNs or ViT and removed during inference. Experimental results conducted on three datasets demonstrate the effectiveness of the proposed approach.

Probability hypothesis density (PHD) filter has been demonstrated a promising algorithm for tracking an unknown number of targets in real time. However, this method can only be used in the multi‐target tracking systems with known measurement noise variances; otherwise, the tracking performance will decline greatly. To solve this problem, an adaptive PHD filter algorithm is proposed based on the variational Bayesian approximation technique to recursively estimate the joint PHDs of the multi‐target states and the time‐varying measurement noise variances. First, the variational calculus method is employed to derive the multi‐target estimate recursions, and then the Gaussian and the inverse Gamma distributions are introduced to approximate the joint posterior PHD, and achieve a closed‐form solution. Simulation results show that the proposed algorithm can effectively estimate the unknown measurement noise variances and has a good performance of multi‐target tracking with a strong robustness.

Fusing a low-resolution hyperspectral (LRHS) image and a high-resolution multispectral (HRMS) image to generate a high-resolution hyperspectral (HRHS) image has grown a significant and attractive application in remote sensing fields. Recently, the popularization of deep learning has injected more possibilities into the fusion work. However, there still exists a difficulty that is how to make the best of the acquired LRHS and HRMS images. In this paper, we present a twice optimizing net with matrix decomposition to fulfill the fusion task, which can be roughly divided into three stages: pre-optimization, deep prior learning, post-optimization. Specifically, we first transform this fusion problem into a spectral optimization problem and a spatial optimization problem with the help of matrix decomposition. These two optimization problems can be handled sequentially by solving a linear equation respectively and then we can obtain the initial HRHS image by multiplying the two solutions. Next, we establish the mapping between the initial image and the reference image through an end-to-end deep residual network based on local and non-local connectivity. In order to get better performance, we have customized a loss function specifically for the fusion task as well. Finally, we return the predicted result again to the optimization procedure to get the final fusion image. After the evaluation on three simulated datasets and one real dataset, it illustrates that the proposed method outperforms many state-of-the-art ones.

The main challenges of remote sensing image scene classification are extracting discriminative features and making full use of the training data. The current mainstream deep learning methods usually only use the hard labels of the samples, ignoring the potential soft labels and natural labels. Self-supervised learning can take full advantage of natural labels. However, it is difficult to train a self-supervised network due to the limitations of the dataset and computing resources. We propose a self-supervised knowledge distillation network (SSKDNet) to solve the aforementioned challenges. Specifically, the feature maps of the backbone are used as supervision signals, and the branch learns to restore the low-level feature maps after background masking and shuffling. The “dark knowledge” of the branch is transferred to the backbone through knowledge distillation (KD). The backbone and branch are optimized together in the KD process without independent pre-training. Moreover, we propose a feature fusion module to fuse feature maps dynamically. In general, SSKDNet can make full use of soft labels and has excellent discriminative feature extraction capabilities. Experimental results conducted on three datasets demonstrate the effectiveness of the proposed approach.

Hyperspectral images have gained great achievements in many fields, but their low-spatial resolution limits the effectiveness in applications. Hyperspectral image super-resolution has emerged as a popular research trend, where high-resolution hyperspectral images are obtained via combing low-resolution hyperspectral images with high-resolution multispectral images. In this process of multi-modality data fusion, it is crucial to ensure effective cross-modality information interaction. To generate higher quality fusion results, a crossed dual-branch U-Net is proposed in this paper. In specific, we adopt U-Net architecture and introduce a spectral-spatial feature interaction module to capture cross-modality interaction information between two input images. To narrow the gap between downsampling and upsampling processes, a spectral-spatial parallel Transformer is designed as skip connection. This novel design simultaneously learns the long-range dependencies both on spatial and spectral information and provides detailed information for final fusion. In the fusion stage, We adopt a progressive upsampling strategy to refine the generated images. Extensive experiments on several public datasets are conducted to prove the performance of the proposed network. The code can be accessed at https://github.com/liuofficial/CD-UNet .