To address the critical challenges in industrial cable surface defect detection—including substantial multi-scale morphological variations, severe background interference, and the inherent trade-off between detection precision and real-time (RT) performance—we propose enhanced multi-scale fusion detection transformer (EMF-DETR), a lightweight yet high-precision model built upon the RT-DETR. Specifically, we introduce a C2f- spatial-frequency attention (SFA) module into the backbone, which integrates Fourier transform with modern convolutional architectures. This design enhances feature extraction by exploiting the global receptive field in the frequency domain while reducing the parameter count. In the encoder, we incorporate a HiLo attention mechanism that decouples high- and low-frequency (Lo-Fi) processing, simultaneously capturing local high-frequency details and global Lo-Fi contextual information. This enables dynamic focus on critical defect regions while suppressing background noise. Furthermore, we propose a hierarchically enhanced fusion pyramid network, which strengthens key semantic information and achieves efficient multi-scale feature fusion through supplementary enhancement pathways and multi-stream aggregation. Experimental results demonstrate that EMF-DETR improves mAP@0.5 by 5.1% while reducing parameters by 3.31 M. Additionally, it achieves mAP@0.5 scores of 92.4% on the CableInspect-AD dataset and 93.7% on the fabric subset of MVTec AD—which exhibits periodic textures analogous to cables—indicating its competitive detection performance and promising cross-domain generalization.

To address micro-break and edge-chipping defects in ferrite magnetic sheets, as well as the difficulty of balancing detection accuracy and deployment cost under complex grinding-texture interference, this paper proposes FMSD-YOLO12, an efficient and lightweight defect detection model based on YOLOv12. The proposed method follows a task-oriented design for three coupled challenges in ferrite magnetic sheet inspection, namely texture-interfered feature extraction, cross-scale feature inconsistency, and lightweight yet accurate defect localization. Specifically, a Spatially Re-weighted Convolution (SR-Conv) is introduced into the C3k2 backbone module to suppress repetitive grinding-texture noise and enhance the response contrast of subtle defect regions. A Context and Spatial Feature Calibration Network (CSFCN) is further developed to improve semantic consistency and spatial alignment during multi-scale feature fusion. In addition, a Lightweight Shared Detail-Enhanced Convolutional Detection head (LSDECD) is designed to strengthen weak-edge localization while reducing parameter redundancy through re-parameterization. Experimental results show that, with a comparable number of parameters, FMSD-YOLO12 improves mAP@50 by 2.40%, mAP@75 by 3.71%, and mAP@50-95 by 3.03% on the magnetic sheet defect dataset. These results demonstrate that the proposed model achieves a favorable balance between detection accuracy and computational efficiency for irregular defect detection under complex industrial backgrounds.

Floating debris detection in complex aquatic environments holds significant importance for water resource protection and maritime safety monitoring. However, this task faces three core challenges: severe background interference leading to blurred target textures, significant non-rigid deformations, and the frequent loss of small targets at long distances. To address these issues, we propose a high-performance lightweight detection algorithm, termed High-Efficiency Edge-Aware Multi-Scale Real-Time Detection Transformer (HEMS-RTDETR), built upon the Real-Time Detection Transformer (RT-DETR) architecture. First, to suppress disturbances induced by water surface ripples and specular reflections, a Cross-Stage Partial Multi-Scale Edge Information Enhancement (CSP-MSEIE) module is introduced to reconstruct the backbone network. By removing computational redundancy while incorporating explicit edge enhancement, feature extraction capability and noise robustness for weak-texture targets are significantly improved. Second, to handle irregular debris morphology, a Deformable Attention Transformer (DAT) module is integrated, enabling adaptive attention focusing on geometrically deformed regions. Finally, an Efficient Multi-Scale Bidirectional Feature Pyramid Network (EMBSFPN) is constructed to enhance cross-scale semantic interaction and alleviate small-target signal loss. Experimental results demonstrate that, compared with RTDETR-r18, HEMS-RTDETR reduces parameters to 12.57 M, improves mAP@0.5 and mAP@0.5:0.95 by 2.44% and 3.05%, respectively, and maintains real-time inference at 93 FPS, indicating strong robustness and application potential in dynamic aquatic environments.