Detecting ships using Synthetic Aperture Radar (SAR) in coastal areas is still difficult due to the impact of coherent speckle noise from the ocean surface, complex land clutter and having multi-scale target representations in the radar imagery. Most of the existing ship detection algorithms lose important target features during downsampling and have difficulty recovering those features through upsampling, resulting in a high number of false detections and missed detections. In this work, we present a new ship detection algorithm called Synergistic Star-Attentive Network with Dynamic Feature Refinement (S²D-Net). First, we create a new backbone called Multi-scale PCCA-StarNet to generate robust feature representations. Within the backbone we implement a Progressive Channel-Coordinate Attention (PCCA) mechanism to create a synergy between global channel filtering and adaptive coordinate locking to decouple ship textures from granular speckle noise. Second, we create a Dynamic Feature Refinement Neck. We develop a content-aware dynamic upsampler called DySample to replace conventional interpolation to improve fidelity of the upsampled feature of small targets. Further, we design a Star-PCCA Feature Aggregation module which fuses features together. Using star-operations and the PCCA mechanism, this module refines semantic features and removes background clutter while aggregating features across multiple scales. Third, we develop a Lightweight Shared Convolutional Detection Head with Quality Estimation (LSCD-LQE). The LSCD-LQE decreases parameter redundancy by using shared convolutional layers and adds a localization quality estimation branch. Therefore, the LSCD-LQE effectively reduces false positive detections through alignment of classification scores with localization quality based on Intersection over Union (IoU) in difficult coastal environments. Our experimental results, using the SSDD and HRSID datasets, show that S²D-Net produces results comparable to representative ship detection algorithms. In particular, on the challenging HRSID inshore subset, our proposed method achieved a mean average precision (mAP) of 82.7%, which is 6.9% greater than the YOLOv11n baseline ship detection algorithm. These results demonstrate that S²D-Net is superior at detecting small coastal vessels and mitigating the detrimental effects of the nearshore complex environment on the performance ship detection using SAR.

Accurate segmentation of marine oil spills in synthetic aperture radar (SAR) images is crucial for emergency response and environmental remediation. However, current deep learning methods are still limited by two long-standing bottlenecks: first, multiplicative speckle noise and complex background clutter make it difficult to accurately delineate actual oil spills; and second, limited receptive fields often lead to the geometric fragmentation of elongated, irregular oil films. To surmount these challenges, this paper proposes a novel framework termed the Frequency-Spatial Coordinate and Strip-Augmented Network (FCS-Net). First, we leverage the ConvNeXt-Small backbone to extract robust hierarchical features, utilizing its large kernel design to capture broad contextual information. Second, a Frequency-Spatial Coordinate Attention (FS-CA) module is proposed to integrate spatial coordinate encoding with global frequency-domain information. Third, to maintain the morphological integrity of elongated targets, we introduce a Strip-Augmented Pyramid Pooling (SAPP) module which employs anisotropic strip pooling to model long-range dependencies. Extensive experiments on the multi-source SOS dataset demonstrate the effectiveness of FCS-Net. The proposed method achieves state-of-the-art performance, reaching an mIoU of 87.78% in the Gulf of Mexico and 89.62% in the challenging Persian Gulf, outperforming strong baselines and demonstrating superior robustness in complex ocean scenarios.

Detecting surface defects in forgings is crucial for ensuring the reliability of automotive components such as steering knuckles. In fluorescent magnetic particle inspection (FDMPI) images, normal forging surfaces generally exhibit locally symmetric texture patterns, whereas cracks and other flaws appear as locally asymmetric regions. Traditional FDMPI inspection relies on manual visual judgement, which is inefficient and error-prone. This paper introduces SDDNet, a symmetry-aware deep learning model for surface defect detection in FDMPI images. A dedicated FDMPI dataset is constructed and further expanded using a denoising diffusion probabilistic model (DDPM) to improve training robustness. To better separate symmetric background textures from asymmetric defect cues, SDDNet integrates a UPerNet-based segmentation layer for background suppression and a Scale-Variant Inception Module (SVIM) within an RTMDet framework for multi-scale feature extraction. Experiments show that SDDNet effectively suppresses background noise and significantly improves detection accuracy, achieving a mean average precision (mAP) of 45.5% on the FDMPI dataset, 19% higher than the baseline, and 71.5% mAP on the NEU-DET dataset, outperforming existing methods by up to 8.1%.

Marine oil spill monitoring plays a critical role in environmental protection and emergency response. Synthetic aperture radar (SAR) provides all-day, all-weather, and wide-area imaging capabilities and has become a primary sensor for operational oil spill surveillance. Nevertheless, SAR oil spill segmentation remains challenging. Real slicks are easily confused with look-alike dark formations; oil film boundaries are weak and fragmented under speckle noise; and small and sparse targets, such as ships, are easily overlooked amid the dominant sea surface background and complex coastal structures. To address these challenges, this paper proposes SDE-Net, an encoder–decoder network built on a ConvNeXtV2-Tiny backbone and a UPerNet-style decoder with three task-oriented modules. The Strip-Directional Local Enhancement (SDLE) module refines elongated low-contrast cues in the shallow lateral features of $C_2$ and $C_3$ while limiting the indiscriminate enhancement of speckle-contaminated responses. The Dynamic Scale Pyramid Context (DSPC) module redesigns pyramid-based context aggregation at the deepest stage by introducing an input-conditioned softmax scale gate that adaptively reweights the contributions of predefined contextual branches. The Edge-Aware Dynamic Gated FPN (EDG-FPN) decoder combines DySample-based feature alignment and dynamic gated fusion with a boundary-aware gate driven by an edge prediction branch, modulating high-level semantic propagation in boundary-sensitive regions without requiring additional edge annotations. On the Oil Spill Detection Dataset, SDE-Net achieves a 72.94% mIoU and 82.88% mDice, outperforming the UPerNet baseline equipped with the same ConvNeXtV2-Tiny backbone by 4.25 and 3.84 percentage points, respectively. The results demonstrate improved oil spill delineation and the preservation of sparse small-class structures under complex SAR sea surface conditions.

Optical-SAR object detectors trained on cloud-free paired imagery tend to develop a strong dependence on the information-rich optical modality. Consequently, the availability of SAR observations does not necessarily guarantee their effective use when optical information becomes unreliable under cloud occlusion. To address this issue, we propose NCMR-Net, a Normality-Calibrated Modality Routing Network that enables spatially adaptive optical-to-SAR routing without image-level cloud augmentation. NCMR-Net retains the standard YOLOv11s detection architecture and introduces three functional modules along the optical-SAR interaction and routing pathway. First, the Frequency-Selective SAR Refinement (FSR) module applies Haar-based subband decomposition and bounded high-frequency correction to construct a more usable SAR fallback representation. Second, the Normality-Calibrated Gating (NCG) module derives non-learnable input-domain evidence from high brightness and reduced local texture, which characterize the optical information collapse associated with cloud degradation. NCG calibrates this evidence against its empirical distribution under normal optical observations. At inference, a lower bound on the SAR mixing coefficient maintains optical-SAR fusion at low NCG responses, while stronger responses increase the SAR coefficient above this bound. Finally, the Gate-Conditioned Residual Adaptation (GCRA) module combines the routing gate with local feature statistics and performs gate-conditioned, identity-initialized residual adaptation across different routing states. In the single-run OSPRC evaluation, NCMR-Net is trained on cloud-free RGB10M-VH pairs without image-level cloud augmentation. Under the matched RGB10M-VH condition, NCMR-Net achieves $85.12\%$${\mathrm{mAP}}_{50}$ and $53.57\%$${\mathrm{mAP}}_{50:95}$, compared with $83.48\%$ and $53.30\%$ for YOLOv11s-Add. Without retraining, fine-tuning, or test-time adaptation, it achieves $64.48\%$${\mathrm{mAP}}_{50}$ under the synthetic cloud-degraded CLUDE-VH condition, exceeding the baseline’s $39.15\%$ by $25.33$ percentage points. The corresponding ${\mathrm{mAP}}_{50}$ retention rates are $75.8\%$ for NCMR-Net and $46.9\%$ for YOLOv11s-Add. These results support improved performance retention under the tested synthetic cloud degradation; generalization to real clouds remains to be established.

Wavelength-conditioned remote sensing foundation models accept flexible spectral configurations, but compatibility does not ensure effective spectral utilization. We investigate this issue for hyperspectral remote sensing salient object detection and propose SpecAudit, an offline framework diagnosing input discriminability, entry-kernel geometry, and layer-wise spectral readability, together with Two-Level Spectral Adaptation (TLSA). On the 32-band hyperspectral remote sensing salient object detection dataset (HRSSD), expanding a Dynamic One-For-All (DOFA)-based pipeline from 3 to 32 bands yields no stable saliency gain. A ground-truth-assisted image-specific diagnostic readout, fitted and evaluated on spatially separated regions of each test image, yields $\Delta S_{\alpha }=+0.0418$, indicating substantial image-specific spectral discriminability despite the absence of a stable direct prediction gain. TLSA combines task-shared Band Amplitude Calibration, using one learnable gain per band before the frozen entry, with Self-Guided Spectral Refinement, which fits an image-specific spectral discriminant from the coarse prediction at inference. Across five training seeds and paired image-level tests, both adaptation levels provide positive incremental improvements. TLSA increases mean $S_{\alpha }$ from 0.6472 to 0.6613, yields a positive paired improvement over the three-band reference, and exceeds the highest mean $S_{\alpha }$ among nine retrained published methods by 3.5%. These results indicate that hyperspectral gains depend on how spectral evidence is exposed and used, not only on available band count. The complete TLSA implementation and SpecAudit diagnostic code will be publicly released upon publication.