Conventional high-speed and spectral imaging systems are expensive and they usually consume a significant amount of memory and bandwidth to save and transmit the high-dimensional data. By contrast, snapshot compressive imaging (SCI), where multiple sequential frames are coded by different masks and then summed to a single measurement, is a promising idea to use a 2-dimensional camera to capture 3-dimensional scenes. In this paper, we consider the reconstruction problem in SCI, i.e., recovering a series of scenes from a compressed measurement. Specifically, the measurement and modulation masks are fed into our proposed network, dubbed BI directional R ecurrent N eural networks with A dversarial T raining (BIRNAT) to reconstruct the desired frames. BIRNAT employs a deep convolutional neural network with residual blocks and self-attention to reconstruct the first frame, based on which a bidirectional recurrent neural network is utilized to sequentially reconstruct the following frames. Moreover, we build an extended BIRNAT-color algorithm for color videos aiming at joint reconstruction and demosaicing. Extensive results on both video and spectral, simulation and real data from three SCI cameras demonstrate the superior performance of BIRNAT.

Due to hardware limitations of the imaging sensors, it is challenging to acquire images of high resolution in both spatial and spectral domains. Fusing a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image (HRMSI) to obtain an HR-HSI in an unsupervised manner has drawn considerable attention. Though effective, most existing fusion methods are limited due to the use of linear parametric modeling for the spectral mixture process, and even the deep learning-based methods only focus on deterministic fully-connected networks without exploiting the spatial correlation and local spectral structures of the images. In this paper, we propose a novel variational probabilistic autoencoder framework implemented by convolutional neural networks, in order to fuse the spatial and spectral information contained in the LR-HSI and HRMSI, called FusionNet. The FusionNet consists of a spectral generative network, a spatial-dependent prior network, and a spatial-spectral variational inference network, which are jointly optimized in an unsupervised manner, leading to an end-toend fusion system. Further, for fast adaptation to different observation scenes, we give a meta-learning explanation to the fusion problem, and combine the FusionNet with meta-learning in a synergistic manner. Effectiveness and efficiency of the proposed method are evaluated based on several publicly available datasets, demonstrating that the proposed FusionNet outperforms the state-of-the-art fusion methods.

Robust and efficient feature extraction is critical for high-resolution range profile (HRRP)-based radar automatic target recognition (RATR). In order to explore the correlation between range cells and extract the structured discriminative features in HRRP, in this paper, we take advantage of the attractive properties of convolutional neural networks (CNNs) to address HRRP RATR and rejection problem. Compared with the time domain representations, the spectrogram of HRRP records the amplitude feature and characterizes the phase information among the range cells. Thus, besides using one-dimensional CNN to handle HRRP in time domain, we also devise a two-dimensional CNN model for the spectrogram feature. Furthermore, by adding a deconvolutional decoder, we integrate the target recognition with outlier rejection task together. Experimental results on measured HRRP data show that our CNN model outperforms many state-of-the-art methods for both recognition and rejection tasks.

To deal with the temporal dependence between range cells in high resolution range profile (HRRP), dynamic methods, especially recurrent neural network (RNN), have been employed to extract features for target recognition. However, RNN has difficulty in complex and diverse sequence modeling problems as it ignores non-stationary sequential relationship between time-steps by sharing same parameters among all time-steps. Given this issue, we propose tensor recurrent neural network with Gaussian mixture model (GmTRNN) for HRRP, not only making use of temporal characteristic but also modeling the variation among its patterns. Specifically, a novel tensor RNN is developed by extending all the parameters in the form of tensor to explore diverse temporal dependence between range cells within an HRRP sample, where a mixture model is introduced to determine the parameters of each time-step in tensor RNN. Moreover, to take advantage of Bayesian nonparametrics in handling the unknown number of mixture components, we further propose the tensor recurrent neural network with Dirichlet process mixture (DPmTRNN). For scalable and joint training of clustering and recognition, we present effective hybrid online variational inference and stochastic gradient descent method. Experiments on benchmark data, measured and simulated HRRP data demonstrate the the effectiveness and efficiency of our models and its robustness to HRRP shift.

In recent years, deep convolutional neural networks (CNNs) pose superior synthetic aperture radar target recognition (SAR-TR) performance. However, CNN-based SAR classifiers would be vulnerable to adversarial attack (AA) when strong nonlinearity of CNN is contrapuntally utilized by AA. The AA can cause a CNN classifier to produce erroneous predictions with extremely high confidence by injecting a tiny adversarial perturbation to the input SAR images. In this letter, an accelerated SAR-TR AA algorithm is proposed named Fast C&W. We introduce a well-trained deep encoder network to replace the process of searching for the optimal perturbation of the input SAR image iteratively in the vanilla C&W algorithm. In this way, an adversarial perturbation can be generated much faster through the rapid forward mapping during an attack. Meanwhile, as a feature extraction network, the encoder network can learn the separable data region by optimizing the attack loss function. Through the encoder network, the added perturbation energy can be mainly concentrated on a region of target instead of background clutter area. This property would be of advantages in the perturbation location control in an SAR image. In the experiments, we use the proposed AA algorithm to interfere with the deep CNN-based high-accuracy SAR-TR model trained on the moving and stationary target acquisition and recognition (MSTAR) data set, which demonstrates its excellent effectiveness and thousands of times of efficiency improvement.