Road extraction from optical remote sensing images has drawn much attention in recent decades and has a wide range of applications. Most of the previous studies rarely take into account the unique topological characteristics of the road. It is the most apparent feature of linear structure that describes the variety of connection relationships of the road. However, designing a particular topological feature extraction network usually results in a model that is too heavy and impractical. To address the problems mentioned above, in this paper, we propose a lightweight topological space network for road extraction based on knowledge distillation (TSKD-Road). Specifically, (1) narrow and short roads easily influence topological features extracted directly in optical remote sensing images. Therefore, we propose a denser teacher network for extracting road structures; (2) to enhance the weight of topological features, we propose a topological space loss calculation model with multiple widths and depths; (3) based on the above innovations, a topological space knowledge distillation framework is proposed, which aims to transfer different kinds of knowledge acquired in a heavy net to a lightweight net, while significantly improving the lightweight net’s accuracy. Experiments were conducted on two publicly available benchmark datasets, which show the obvious superiority and effectiveness of our network.

Since polarimetric synthetic aperture radar (PolSAR) terrain segmentation is a dense prediction task, the disadvantage of inadequate labeled samples greatly limits its performance. In this paper, we present a semi-supervised segmentation network called SemiPSCN to reduce the data reliance on label annotation, which integrates semi-supervised learning paradigm and the characteristics of PolSAR data into a unified architecture. First, considering the unreliability of pseudo-labels caused by noise interference in PolSAR data, a pseudo-label error localization (PEL) module is designed. By mapping the pixels that have mispredictions in pseudo-labels, PEL can greatly enhance the confidence of pseudo-labels. Then, SemiPSCN introduces a category representation constraint (CRC) module to explicitly boost the category consistency between labeled and unlabeled PolSAR data. Via explicit intra-category and inter-category constraints, CRC can guarantee the invariant representations on the same category region between labeled and unlabeled data. Furthermore, a region consistency constraint (RCC) module is designed to enhance the regional consistency in PolSAR data. RCC leverages the conception of graph to model the understanding of spatial relations among terrain targets, thereby facilitating consistent spatial region expression in semi-supervised process. Finally, we build a challenging large-scale dataset called LSPolSAR-Seg and conduct abundant experiments on LSPolSAR-Seg. SemiPSCN exhibits superior performance when compared to other advanced approaches, especially improving mIoU by 3.44% 12.77% under 20% split setting, which promotes the performance to a state-of-the-art level.

Synthetic aperture radar (SAR) ship detection and classification has gained unprecedented attention due to its important role in maritime transportation. Many deep learning-based detectors and classifiers have been successfully applied and achieved great progress. However, ships in SAR images present discrete and multi-centric features, and their scattering characteristics and edge information are sensitive to variations in target attitude angles (TAAs). These factors pose challenges for existing methods to obtain satisfactory results. To address these challenges, a novel target attitude angle-guided network (TAG-Net) is proposed in this article. The core idea of TAG-Net is to leverage TAA information as guidance and use an adaptive feature-level fusion strategy to dynamically learn more representative features that can handle the target imaging diversity caused by TAA. This is achieved through a TAA-aware feature modulation (TAFM) module. It uses the TAA information and foreground information as prior knowledge and establishes the relationship between the ship scattering characteristics and TAA information. This enables a reduction in the intra-class variability and highlights ship targets. Additionally, considering the different requirements of the detection and classification tasks for the scattering information, we propose a layer-wise attention-based task decoupling detection head (LATD). Unlike general deep learning methods that use shared features for both detection and classification tasks, LATD extracts multi-level features and uses layer attention to achieve feature decoupling and select the most suitable features for each task. Finally, we introduce a novel salient-enhanced feature balance module (SFB) to provide richer semantic information and capture the global context to highlight ships in complex scenes, effectively reducing the impact of background noise. A large-scale ship detection dataset (LSSDD+) is used to verify the effectiveness of TAG-Net, and our method achieves state-of-the-art performance.

Synthetic Aperture Radar (SAR) ship target detection has been extensively researched. However, most methods use the same dataset division for both training and validation. In practical applications, it is often necessary to quickly adapt to new loads, new modes, and new data to detect targets effectively. This presents a cross-domain detection problem that requires further study. This paper proposes a method for detecting SAR ships in complex backgrounds using fusion tensor and cross-domain adversarial learning. The method is designed to address the cross-domain detection problem of SAR ships with large differences between the training and test sets. Specifically, it can be used for the cross-domain detection task from the fully polarised medium-resolution ship dataset (source domain) to the high-resolution single-polarised dataset (target domain). This method proposes a channel fusion module (CFM) based on the YOLOV5s model. The CFM utilises the correlation between polarised channel images during training to enrich the feature information of single-polarised images extracted by the model during inference. This article proposes a module called the cross-domain adversarial learning module (CALM) to reduce overfitting and achieve adaptation between domains. Additionally, this paper introduces the anti-interference head (AIH) which decouples the detection head to reduce the conflict of classification and localisation problems. This improves the anti-interference and generalisation ability in complex backgrounds. This paper conducts cross-domain experiments using the constructed medium-resolution SAR full polarisation dataset (SFPD) as the source domain and the high-resolution single-polarised ship detection dataset (HRSID) as the target domain. Compared to the best-performing YOLOV8s model among typical mainstream models, this model improves precision by 4.9%, recall by 3.3%, AP by 2.4%, and F1 by 3.9%. This verifies the effectiveness of the method and provides a useful reference for improving cross-domain learning and model generalisation capability in the field of target detection.

Synthetic Aperture Radar (SAR) aircraft detection plays a crucial role in various civilian applications. Benefiting from the powerful capacity of feature extraction and analysis of deep learning, aircraft detection performance has been improved by most traditional general-purpose visual intelligence methods. However, the inherent imaging mechanisms of SAR fundamentally differ from optical images, which poses challenges for SAR aircraft detection. Aircraft targets in SAR imagery typically exhibit indistinct details, discrete features, and weak contextual associations and are prone to non-target interference, which makes it difficult for existing visual detectors to capture critical features of aircraft, limiting further optimization of their performance. To address these issues, we propose the scattering feature guidance network (SFG-Net), which integrates feature extraction, global feature fusion, and label assignment with essential scattering distribution of targets. This enables the network to focus on critical discriminative features and leverage robust scattering features as guidance to enhance detection accuracy while suppressing interference. The core components of the proposed method include the detail feature supplement (DFS) module and the context-aware scattering feature enhancement (CAFE) module. The former integrates low-level texture and contour features to mitigate detail ambiguity and noise interference, while the latter leverages global context of strong scattering information to generate more discriminative feature representations, guiding the network to focus on critical scattering regions and improving learning of essential features. Additionally, a feature scattering center-based label assignment (FLA) strategy is introduced, which utilizes the spatial distribution of scattering information to adaptively adjust the sample coverage and ensure that strong scattering regions are prioritized during training. A series of experiments was conducted on the CSAR-AC dataset to validate the effectiveness and generalizability of the proposed method.

Synthetic Aperture Radar (SAR) ship target detection has been extensively researched. However, most methods use the same dataset division for both training and validation. In practical applications, it is often necessary to quickly adapt to new loads, new modes, and new data to detect targets effectively. This presents a cross-domain detection problem that requires further study. This paper proposes a method for detecting SAR ships in complex backgrounds using fusion tensor and cross-domain adversarial learning. The method is designed to address the cross-domain detection problem of SAR ships with large differences between the training and test sets. Specifically, it can be used for the cross-domain detection task from the fully-polarised medium-resolution ship dataset (source domain) to the high-resolution single-polarised dataset (target domain). This method proposes a Channel Fusion Module (CFM) based on the YOLOV5s model. The CFM utilises the correlation between polarised channel images during training to enrich the feature information of single-polarised images extracted by the model during inference. The article proposes a module called Cross-Domain Adversarial Learning Module (CALM) to reduce overfitting and achieve adaptation between domains. Additionally, the paper introduces the Anti-Interference Head (AIH) which decouples the detection head to reduce the conflict of classification and localization problems. This improves the anti-interference and generalization ability in complex backgrounds. This paper conducts cross-domain experiments using the constructed medium-resolution SAR full polarization dataset (SFPD) as the source domain and the high-resolution single-polarised ship detection dataset (HRSID) as the target domain. Compared to the best-performing YOLOV8s model among typical mainstream models, this model improves Precision by 4.9%, Recall by 3.3%, AP by 2.4%, and F1 by 3.9%. This verifies the effectiveness of the method and provides a useful reference for improving cross-domain learning and model generalization capability in the field of target detection.