After the revival of deep learning in computer vision in 2012, SAR ship detection comes into the deep learning era too. The deep learning-based computer vision algorithms can work in an end-to-end pipeline, without the need of designing features manually, and they have amazing performance. As a result, it is also used to detect ships in SAR images. The beginning of this direction is the paper we published in 2017BIGSARDATA, in which the first dataset SSDD was used and shared with peers. Since then, lots of researchers focus their attention on this field. In this paper, we analyze the past, present, and future of the deep learning-based ship detection algorithms in SAR images. In the past section, we analyze the difference between traditional CFAR (constant false alarm rate) based and deep learning-based detectors through theory and experiment. The traditional method is unsupervised while the deep learning is strongly supervised, and their performance varies several times. In the present part, we analyze the 177 published papers about SAR ship detection. We highlight the dataset, algorithm, performance, deep learning framework, country, timeline, etc. After that, we introduce the use of single-stage, two-stage, anchor-free, train from scratch, oriented bounding box, multi-scale, and real-time detectors in detail in the 177 papers. The advantages and disadvantages of speed and accuracy are also analyzed. In the future part, we list the problem and direction of this field. We can find that, in the past five years, the AP₅₀ has boosted from 78.8% in 2017 to 97.8 % in 2022 on SSDD. Additionally, we think that researchers should design algorithms according to the specific characteristics of SAR images. What we should do next is to bridge the gap between SAR ship detection and computer vision by merging the small datasets into a large one and formulating corresponding standards and benchmarks. We expect that this survey of 177 papers can make people better understand these algorithms and stimulate more research in this field.

Specific emitter identification (SEI) refers to the technology that uses the inherent defects of the physical layer of a hardware device to identify and uniquely associate a single emitter. Given its unique capability to automatically extract high-dimensional features, deep learning has recently shown great potential in SEI. However, the training process of supervised neural networks largely depends on the generalization of sample distribution and integrity of data labels. In specific non-cooperative areas such as electronic reconnaissance and spectrum monitoring, the unknown radio frequency devices and the complexity of the electromagnetic environment make it difficult to utilize sufficient labeled samples and capture the potential distribution of the data. Therefore, we introduce semi-supervised learning into SEI and propose a self-classification generative adversarial network (GAN) using bispectrum-based feature extraction. The bispectrum estimation of the signal is used as the feature representation of emitters, and the label information is embedded into the input latent layer to guide the training of the GAN. The shared weight update of the classification network is realized through semi-supervised training, and the optimization function of the generator is redefined to solve the mode collapse caused by the game principle. We innovatively extend SEI to communication scenarios with multiple relays and evaluate the effectiveness of our algorithm in different communication scenarios with contaminated radio-frequency fingerprints. The algorithm is also verified using Universal Software Radio Peripheral based on software-defined radio platforms. The numerical experimental results on six modulation signals demonstrate the excellent semi-supervised classification performance of the proposed SEI scheme in multiple scenarios.

Better neural networks, more powerful computer hardware and signal Big Data make deep learning increasingly important in Specific Emitter Identification (SEI). However, its implementation uses large amounts of resources and releases CO2. With the requirement of green and low-carbon resource sustainability, deep learning-based SEI faces the great challenge of compressing the model while ensuring its performance. In this article, we propose a novel green and low resource specific emitter identification method using complex networks and Fisher pruning (GLR-SEI). Specifically, we divide the learning process into two stages: knowledge distillation and fisher pruning, which involves transferring knowledge from complex number networks to real number networks. The proposed approach is evaluated using aircraft Automatic Dependent Surveillance Broadcast (ADS-B) data collected in the real world and many pruning experiments are performed. In addition, we add descriptive experiments on Raspberry Pi to provide a more effective data presentation in order to better demonstrate our research results. The experimental results show that the proposed lightweight network in this article can reduce the recognition rate by only 0.7% and the inference time by 10.1% compared to the complex neural network.

Decentralized Federated Learning (DeFL) plays a critical role in improving effectiveness of training and has been proved to give great scope to the development of edge computing. However, on the one hand, inaccessibility of private data and excessively exploiting the data throughout the learning process have become a public concern, and on the other hand the connections between server-less edge devices are always varying due to the mobility of edge intelligent devices. To address the above issues, we propose a P rivacy- E nhanced - D ynamic - D ecentralized - F ederated - L earning algorithm called PED $ ^{2}$ FL in a dynamic edge environment. We design the PED $ ^{2}$ FL under the analog transmission scheme, where mobile edge devices transmit privacy preserving data simultaneously and accomplish efficient information aggregation with doubly-stochastic adjacent matrices. With thorough analysis, it can be demonstrated that PED $ ^{2}$ FL satisfies $(\epsilon,\delta)$ -differential privacy while the per-device privacy budget decays exponentially with the number of the neighbors, which greatly improved the data utility compared to the fixed budget in the orthogonal transmission strategy. PED $ ^{2}$ FL has the same convergence rate $\mathcal {O}(\sqrt{\frac{1}{KN}})$ as the non-private decentralized learning algorithm D-PSGD without enhanced privacy protection, where $K$ and $N$ are the total iterations and the number of nodes, respectively. Extensive experiments show that algorithm PED $ ^{2}$ FL also performs well with real-world settings.

Recently, deep learning (DL) has been successfully applied in automatic target recognition (ATR) tasks of synthetic aperture radar (SAR) images. However, limited by the lack of SAR image target datasets and the high cost of labeling, these existing DL based approaches can only accurately recognize the target in the training dataset. Therefore, high precision identification of unknown SAR targets in practical applications is one of the important capabilities that the SAR–ATR system should equip. To this end, we propose a novel DL based identification method for unknown SAR targets with joint discrimination. First of all, the feature extraction network (FEN) trained on a limited dataset is used to extract the SAR target features, and then the unknown targets are roughly identified from the known targets by computing the Kullback–Leibler divergence (KLD) of the target feature vectors. For the targets that cannot be distinguished by KLD, their feature vectors perform t-distributed stochastic neighbor embedding (t-SNE) dimensionality reduction processing to calculate the relative position angle (RPA). Finally, the known and unknown targets are finely identified based on RPA. Experimental results conducted on the MSTAR dataset demonstrate that the proposed method can achieve higher identification accuracy of unknown SAR targets than existing methods while maintaining high recognition accuracy of known targets.

Hyperspectral video with spatial and spectral information has great potential to improve object tracking performance. However, the limited hyperspectral training samples hinder the development of hyperspectral object tracking. Since hyperspectral data has multiple bands, from which any three bands can be extracted to form pseudocolor images, we propose a Transformer-based multimodality information transfer network (TMTNet), aiming to improve the tracking performance by efficiently transferring the information of multimodality data composed of RGB and hyperspectral in the hyperspectral tracking process. The multimodality information needed to be transferred mainly includes the RGB and hyperspectral multimodality fusion information and the RGB modality information. Specifically, we construct two subnetworks to transfer the multimodality fusion information and the robust RGB visual information, respectively. Among them, the multimodality fusion information transfer subnetwork is designed based on the dual Siamese branch structure. The subnetwork employs the pretrained RGB tracking model as the RGB branch to guide the training of the hyperspectral branch with little training samples. The RGB modality information transfer subnetwork is designed based on a pretrained RGB tracking model with good performance to improve the tracking network’s generalization and accuracy in unknown complex scenes. In addition, we design an information interaction module based on Transformer in the multimodality fusion information transfer subnetwork. The module can fuse multimodality information by capturing the potential interaction between different modalities. We also add a spatial optimization module to TMTNet, which further optimizes the object position predicted by the subject network by fully retaining and utilizing detailed spatial information. Experimental results on the only available hyperspectral tracking benchmark dataset show that the proposed TMTNet tracker outperforms the advanced trackers, demonstrating the effectiveness of this method.