Many deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN), have been successfully applied to extracting deep features for hyperspectral tasks. Hyperspectral image classification allows distinguishing the characterization of land covers by utilizing their abundant information. Motivated by the attention mechanism of the human visual system, in this study, we propose a spectral-spatial attention network for hyperspectral image classification. In our method, RNN with attention can learn inner spectral correlations within a continuous spectrum, while CNN with attention is designed to focus on saliency features and spatial relevance between neighboring pixels in the spatial dimension. Experimental results demonstrate that our method can fully utilize the spectral and spatial information to obtain competitive performance.

Anomaly detection of hyperspectral data has been gaining particular attention for its ability in detecting targets in an unsupervised manner. Autoencoder (AE), together with its variants can not only extract intrinsic features automatically but also detect anomalies that differ dramatically from others. Many AE-driven algorithms are, thus, proposed for anomaly detection in hyperspectral imagery (HSI), but they suffer from two problems: 1) when there exist anomalies in the training set, AE can generalize so well that it can also learn the abnormal patterns well, thereby reducing the ability to distinguish anomalies from the background and 2) geometric structure among samples are lost in latent space of AE, which is vital in hyperspectral anomaly detection. To tackle these problems, we propose a robust anomaly detector based on the AE framework, named robust graph AE (RGAE) detector, in this article. To be specific, we propose a robust AE framework with $\ell _{2,1}$ -norm that is robust to noise and anomalies during training. Meanwhile, we embed a superpixel segmentation-based graph regularization term (SuperGraph) into AE. This strategy can preserve the geometric structure and the local spatial consistency of HSI simultaneously and also effectively reduce the searching space and execution time for each pixel. Extensive experiments are conducted on five datasets, and the results demonstrate that our method has a better detection performance, after comparing with other state-of-the-art hyperspectral anomaly detectors.

Effective and efficient infrared (IR) small target detection is essential for IR search and tracking (IRST) systems. The current methods have some limitations in background suppression or detection of targets close to each other. In this letter, a double-neighborhood gradient method (DNGM) is proposed. First, a new technology of the tri-layer sliding window is designed to measure the double-neighborhood gradient. Then, the DNGM is obtained by multiplying the double-neighborhood gradient. In this way, even the sizes of the targets may vary, ranging from $2 \times 1$ to $9 \times 9$ pixels, the target can be better highlighted under a fixed scale, and background interference can be suppressed. Finally, the target is segmented from the DNGM salience map by an adaptive threshold. Experiments illustrate that the proposed method can avoid the “expansion effect” of the traditional multiscale human vision system (HVS) method and can accurately detect multiple targets close to each other. Besides, the proposed method is more robust and real-time than the existing methods.

Spectral unmixing (SU), which refers to extracting basic features (i.e., endmembers) at the subpixel level and calculating the corresponding proportion (i.e., abundances), has become a major preprocessing technique for the hyperspectral image analysis. Since the unmixing procedure can be explained as finding a set of low-dimensional representations that reconstruct the data with their corresponding bases, autoencoders (AEs) have been effectively designed to address unsupervised SU problems. However, their ability to exploit the prior properties remains limited, and noise and initialization conditions will greatly affect the performance of unmixing. In this article, we propose a novel technique network for unsupervised unmixing which is based on the adversarial AE, termed as adversarial autoencoder network (AAENet), to address the above problems. First, the image to be unmixed is assumed to be partitioned into homogeneous regions. Then, considering the spatial correlation between local pixels, the pixels in the same region are assumed to share the same statistical properties (means and covariances) and abundance can be modeled to follow an appropriate prior distribution. Then the adversarial training procedure is adapted to transfer the spatial information into the network. By matching the aggregated posterior of the abundance with a certain prior distribution to correct the weight of unmixing, the proposed AAENet exhibits a more accurate and interpretable unmixing performance. Compared with the traditional AE method, our approach can greatly enhance the performance and robustness of the model by using the adversarial procedure and adding the abundance prior to the framework. The experiments on both the simulated and real hyperspectral data demonstrate that the proposed algorithm can outperform the other state-of-the-art methods.

Extracting small targets from complex backgrounds is the eventual goal of single-frame infrared small target detection, which has many potential applications in defense security and marine rescue. Recently, methods utilizing deep learning have shown their superiority over traditional theoretical approaches. However, they do not consider both the global semantics and specific shape information, thereby limiting their performance. To overcome this proplem, we propose a gated-shaped TransUnet (GSTUnet), designed to fully utilize shape information while detecting small target detection. Specifically, we have proposed a multiscale encoder branch to extract global features of small targets at different scales. Then, the extracted global features are passed through a gated-shaped stream branch that focuses on the shape information of small targets through gate convolutions. Finally, we fuse their features to obtain the final result. Our GSTUnet learns both global and shape information through the aforementioned two branches, establishing global relationships between different feature scales. The GSTUnet demonstrates excellent evaluation metrics on various datasets, outperforming current state-of-the-art methods.

In this paper, we propose a novel end-to-end model for fusing medical images characterizing structural information, i.e., IS, and images characterizing functional information, i.e., IF, of different resolutions, by using a multi-generator multi-discriminator conditional generative adversarial network (MGMDcGAN). In the first cGAN, the generator aims to generate a real-like fused image based on a specifically designed content loss to fool two discriminators, while the discriminators aim to distinguish the structure differences between the fused image and source images. On this basis, we employ the second cGAN with a mask to enhance the information of dense structure in the final fused image, while preventing the functional information from being weakened. Consequently, the final fused image is forced to concurrently keep the structural information in IS and the functional information in IF. In addition, as a unified method, MGMDcGAN can be applied to different kinds of medical image fusion, i.e., MRI-PET, MRI-SPECT, and CT-SPECT, where MRI and CT are two kinds of IS of high resolution, PET and SPECT are typical kinds of IF of low resolution. Qualitative and quantitative experiments on publicly available datasets demonstrate the superiority of our MGMDcGAN over the state-of-the-art.