The recognition of synthetic aperture radar (SAR) jamming has gained significant attention due to its critical role in enhancing radar system performance in complex electromagnetic environments. However, existing research typically addresses a limited number of jamming categories, hindering practical applications that require the simultaneous identification of multiple jamming sources. Moreover, the challenges in feature distribution optimization lead to overlaps in inter-class features and inconsistencies within intra-class features, leading to a decrease in the accuracy of SAR jamming recognition. To tackle these issues, we propose a time-frequency aware hierarchical feature optimization method for SAR jamming recognition. Specifically, we propose a timefrequency aware dual attention mechanism to focus on crucial features in the time-frequency map of SAR jamming signal through parallel attention and unified attention. In addition, we propose a hierarchical jamming feature distribution optimization method that further improves the compactness and discrimination of SAR jamming feature representation. We construct an SAR jamming signal dataset with 50 jamming types to validate the proposed recognition method. The detailed results of ablative experiments and comparative experiments demonstrate the superior performance across different JNR conditions achieved by our method, establishing its efficacy for robust SAR jamming recognition.

Semi-supervised segmentation presents a promising approach for large-scale medical image analysis, effectively reducing annotation burdens while achieving comparable performance. This methodology holds substantial potential for streamlining the segmentation process and enhancing its feasibility within clinical settings for translational investigations. While cross-supervised training, based on distinct co-training sub-networks, has become a prevalent paradigm for this task, addressing critical issues such as predication disagreement and label-noise suppression requires further attention and progress in cross-supervised training. In this paper, we introduce an Evidential Tri-Branch Consistency learning framework (ETC-Net) for semi-supervised medical image segmentation. ETC-Net employs three branches: an evidential conservative branch, an evidential progressive branch, and an evidential fusion branch. The first two branches exhibit complementary characteristics, allowing them to address prediction diversity and enhance training stability. We also integrate uncertainty estimation from the evidential learning into cross-supervised training, mitigating the negative impact of erroneous supervision signals. Additionally, the evidential fusion branch capitalizes on the complementary attributes of the first two branches and leverages an evidence-based Dempster-Shafer fusion strategy, supervised by more reliable and accurate pseudo-labels of unlabeled data. Extensive experiments conducted on LA, Pancreas-CT, and ACDC datasets demonstrate that ETC-Net surpasses other state-of-the-art methods for semi-supervised segmentation. The code will be made available in the near future at https://github.com/Medsemiseg.

Automatic modulation classification (AMC), as a key technology of cognitive radio, has become a focal point of research. However, most deep learning-based AMC methods require an extensive number of labeled signals to acquire a comprehensive understanding of modulation types, placing substantial pressure on signal acquisition and labeling. To solve this issue, we propose a few-shot AMC (FSAMC) method to facilitate rapid generalization and recognition with limited data, namely multi-scale feature fusion and distribution similarity network (MS2F-DS). Firstly, we design a multi-scale feature fusion (MS2F) model, which aims to extract features with varying fields of view and boost feature fusion, enabling the derivation of contextual information from the signal. Furthermore, we introduce a distribution similarity (DS) classifier to address the insufficient measurement of current similarity measurement functions by considering both micro and macro perspectives of vectors, further increasing intra-class compactness and inter-class separability. Finally, extensive experiments were conducted on 3-way 1, 3, and 5-shot FSAMC tasks using public datasets RML2016.10a and RML2016.10b, and the results demonstrated the effectiveness of our method.

RGB-Thermal semantic segmentation (SS) aims to combine visual light and thermal images to determine the semantic category for each pixel and create an object mask. While existing methods typically rely on well-aligned RGB-T image pairs, real-world RGB-T pairs are often unaligned, and pixel-by-pixel alignment is both challenging and time-consuming. To address this critical issue, we introduce a new unaligned RGB-T SS benchmark and propose the deformation-resilient multigranularity learning (DML) method. DML explores the spatial consistency and modal complementarity of RGB-T and mitigates the interference of warped modalities by aligning multimodal features in a coarse-to-fine multigranularity strategy. Specifically, DML constructs a deformation-aware complementary feature enhancer (DCFE), which consists of deformation-aware feature alignment (DFA) and complementary feature aggregation (CFA) modules. DFA enhances the spatial alignment of RGB-T by estimating the deformation field of warped features. Then, CFA aggregates complementary contexts of modal differences across multiple scales to produce deformation-resilient and robust RGB-T feature representations. Finally, we design the multigranularity mask refinement engine (MMFE), which combines class-agnostic saliency prediction (CSP) and class-aware edge generation (CEG) auxiliary tasks to provide useful boundary and positional cues for SS decoders. The MMFE enhances semantic alignment and interclass separability, yielding object masks with sharp boundaries. Quantitative and qualitative experiments on aligned and unaligned datasets validate the effectiveness of our proposed DML, consistently outperforming existing methods designed for aligned RGB-T data. The new unaligned RGB-T SS benchmark and code are available at https://github.com/VisionVerse/Unaligned-RGBT-Semantic-Segmentation.

Radar jamming identification is a key technology in radar anti-jamming systems, providing a foundation for intelligent countermeasure decision-making. To address the limitations in multi domain feature fusion of radar jamming signals, this paper proposes a method based on Multi-Domain Fusion for Semantic Graph Reasoning (SGR-MDF). A dual-domain feature interaction network is designed to enable adaptive complementarity and joint enhancement of time- and frequency-domain features. Multi-level features from the time, frequency, and time-frequency domains are then fused to improve signal representation. A graph convolutional classifier is introduced to model both comprehensive and core semantic relationships among jamming types, enhancing classification performance. Experimental results on a dataset comprising 50 jamming types demonstrate that the proposed method achieves a recognition accuracy of 98.68% at a jamming-to-noise ratio (JNR) of 0 dB, outperforming state-of-the-art approaches and exhibiting strong robustness under low-JNR conditions.

In recent years, deep learning has achieved remarkable success in synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of most deep learning-based models heavily depends on a large quantity of high-quality labeled data, which presents severe challenges in the collection and annotation of SAR images. To improve the stability and accuracy of few-shot SAR ATR, we propose a multi-level contrastive learning driven and dependency matrix measured method, termed MCL-DMM. This method comprises two key components: the multi-level contrastive learning (MCL) module and the dependency matrix-based measurement (DMM) module. The MCL module enhances model performance by integrating both individual and cluster discriminative tasks, thereby leading to a plausible and powerful representation learning at both the individual and cluster level. This module aims to construct a robust and unbiased feature extractor with good intra-class tightness and inter-class separateness. Building on this foundation, the DMM module models the dependencies within the feature matrix, providing a comprehensive measurement for few-shot SAR ATR. The cooperation between the robust feature extractor and the precise classifier enables the model to achieve superior performance. Experimental results on the standard MSATR dataset demonstrate that MCL-DMM outperforms current models, positioning it as a highly efficient solution for few-shot SAR ATR.