Cognitive radio (CR) facilitates efficient spectrum management and optimization in wireless networks with massive wireless access and data transmission demands, where spectrum sensing is a prerequisite for dynamic spectrum management. Current neural network-based methods tend to construct discriminative statistical measures as input of networks or implement more complex architectures to improve spectrum sensing performance, failing to consider the complementarity between different statistical measures. Furthermore, the existing methods represent received signals as fixed-size matrices within Euclidean space, which cannot be reused across various access devices equipped with differing numbers of receiving antennas. To alleviate the above issues, this work proposes a Multiplex Graph Convolutional Network-based spectrum sensing (MGCN-SS) framework. First, multiplex networks integrating multi-view and graph structure are constructed as the input. The multiplex network employs a hierarchical structure composed of multiple independent homogeneous graphs to construct the multi-view structure. Each network layer corresponds to a view, which is represented in the form of a homogeneous graph. The dependencies among different views are encoded by the coupling adjacency matrix in the multiplex network. Then, the multiplex graph convolution, composed of intralayer graph convolution and interlayer graph convolution, is used to extract high-level cross-view fusion features. Specifically, the intralayer graph convolution utilizes graph spectral convolution to aggregate node representations and smooth the noise interference within the graph. The interlayer graph convolution introduces the attention mechanism to assign different weights to each view, preventing any specific view from dominating the learning process. Extensive experimental results illustrate that the MGCN-SS surpasses the deep learning-based and conventional methods regarding detection performance and demonstrates strong generalization capabilities.

Image denoising is a key component of digital image processing systems. The latest advances in deep learning have led to significant improvements in denoising techniques, particularly through complementary learning methods that integrate content learning and noise learning. However, existing complementary learning methods typically adopt parallel structures, where the content and noise learning branches run independently and their outputs are directly combined together. Therefore, the two learning methods cannot utilize the effective information in each other's outputs, which results in the information not being fully utilised. To overcome this limitation, we propose a multi-stage cascaded complementary learning (MSCCL) method, which employs a cascaded architecture of noise and content predictors to achieve effective complementary learning. Furthermore, a cross-stage feature fusion strategy is designed to enable effective integration of feature maps between the noise stage and content stage. Experimental results demonstrate that the proposed MSCCL method achieves superior denoising performance compared to previous approaches, under both additive white Gaussian noise and real-world noise conditions.

In recent years, deep learning has emerged as one of the most widely utilized techniques in hyperspectral anomaly detection (HAD) with an impressive detection accuracy. However, the investigation into the diverse background representation and the spatial-spectral interaction remains underexplored. To tackle with this, we propose a novel framework namely the prototype-guided and spatial-spectral interaction network (PSSIN) for HAD in this paper. Specifically, an adaptive anomaly mask module is utilized to mitigate the interference of the background reconstruction caused by the blending of potential anomalies. Subsequently, we design a background-guided prototype autoencoder (BP-AE) to represent the backgrounds with various land cover types, incorporating two critical components: the background prototype module (BPM) and the spatial spectral interaction block (SSIB). To characterize different typical background features by a global perspective, BPM utilizes a prototype learning strategy with a self-attention mechanism, and a multivariate ensemble loss is employed for BPM to optimize the transformation of background features and the updating of a prototype codebook. To enhance the spatial-spectral utilization of window-based approach, SSIB first introduce a spatial-spectral interaction paradigm for HAD. The window-based self-attention branch is to mine spatial features characteristics, while the depth-wise convolution branch is to extract spectral features. These two branches in a parallel configuration interact with each other's features and then perform feature fusion. SSIB architecture not only broadens the receptive fields by concurrently modeling the intra-window and cross-window relationships but also facilitates bi-directional interactions between the spatial and spectral branches. Furthermore, the comprehensive experiments conducted on six authentic datasets have fully validated its superior performance.

Hyperspectral anomaly detection (HAD) aims to identify targets that are significantly different from their surrounding background, employing an unsupervised paradigm. Recently, detectors based on autoencoder (AE) have become predominant methods and demonstrated satisfactory performance. However, there are still two problems that need to be solved. Firstly, the hypothesis that the AE-based models can effectively reconstruct background samples while anomalies cannot, may not always be true in practice, due to their powerful capability for feature extraction. Secondly, the AE-based models primarily concentrate on the quality of sample reconstruction, regardless of whether the encoded features signify the anomalies or background, which is not conducive to the separation of anomalies from the background. To handle the above-mentioned problems, a novel memory-augmented autoencoder (MAAE) model is developed to better reconstruct the background and suppress anomalies reconstruction. Specifically, for the first problem, a novel superpixel-guided adaptive weight calculation (SAWC) module is devised to generate adaptive weights (AWs) by taking into account contextual information in the error map, and then the AWs are incorporated into the reconstruction loss, where the potential background samples are endowed with larger AWs than anomalies during training. For the second problem, a novel sample attribution mining (SAM) module is developed to mine sample attribution (i.e., explore whether a certain sample belongs to the background or anomaly), and the mined background and anomaly samples are employed to train different modules for better separating the anomalies and background. Additionally, an entropy-based sparse addressing (ESA) module is further designed to weaken the reconstruction ability for anomaly samples by designing a learnable sparse addressing weight for memory module. The ablation study validates the effectiveness of the proposed SAWC, SAM, and ESA. Extensive comparison experiments on six hyperspectral image datasets demonstrate the superiority in terms of comprehensive detection performance and background suppression of our method.

Weakly supervised object detection (WSOD) in remote sensing images (RSIs) has attracted lots of attention because it solely employs image-level labels to drive the model training. Most of the WSOD methods incline to mine salient object as positive instance, and the less salient objects are considered as negative instances, which will cause the problem of missing instances. In addition, the quantity of hard and easy instances is usually imbalanced, consequently, the cumulative loss of a large amount of easy instances dominates the training loss, which limits the upper bound of WSOD performance. To handle the first problem, a complementary detection network (CDN) is proposed, which consists of a complementary multiple instance detection network (CMIDN) and a complementary feature learning (CFL) module. The CDN can capture robust complementary information from two basic multiple instance detection networks (MIDNs) and mine more object instances. To handle the second problem, an instance difficulty evaluation metric named instance difficulty score (IDS) is proposed, which is employed as the weight of each instance in the training loss. Consequently, the hard instances will be assigned larger weights according to the IDS, which can improve the upper bound of WSOD performance. The ablation experiments demonstrate that our method significantly increases the baseline method by large margins, i.e. 23.6% (10.2%) mAP and 32.4% (13.1%) CorLoc gains on the NWPU VHR-10.v2 (DIOR) dataset. Our method obtains 58.1% (26.7%) mAP and 72.4% (47.9%) CorLoc on the NWPU VHR-10.v2 (DIOR) dataset, which achieves better performance compared with seven advanced WSOD methods.

Weakly supervised object detection in remote sensing image (RSI) is still a challenge because of the lack of instance-level labels, and many existing methods have two problems. Firstly, most of the existing methods usually mine the pseudo ground truth (PGT) instances solely relying on proposal class scores (PCS). Actually, the reliability of PCS is not enough because of the bird’s eye view imaging and large-scale chaotic background of RSIs, and the instances with high PCS incline to cover the discriminative region rather than the whole object. Secondly, the existing methods assign a one-hot label to each instance, and the label of PGT instance is copied to its neighbor instances, which induces the misclassification problem to some extent. Actually, the probability that the neighbor instances contain the object with the same category is smaller than the PGT instance. For the first problem, the proposal quality score (PQS) is proposed for mining high-quality PGT instances, which contains PCS and dual-context projection score (DCPS). The DCPS is calculated through semantic segmentation, and is employed to measure the completeness that each proposal covers an object. For the second problem, a pseudo soft label assignment (PSLA) strategy is proposed to assign more precise soft label for each instance, where the soft label is determined by the spatial distance between each instance and its nearest PGT instance. The ablation study validates the effectiveness of the PQS and PSLA. The comprehensive comparisons with other WSOD methods on three popular benchmarks show the excellent performance of our method.