Railroad transmission line foreign object detection based on multi-scale adaptive kernel deep feature fusion and channel pruning

Adaptive spectral-spatial feature fusion network for hyperspectral image classification using limited training samples

The fully convolutional networks (FCNs) have been widely applied in numerous medical image segmentation tasks. However, tissue regions usually have large variations of shape and scale, so the ability of neural networks to learn multi-scale features is important to the segmentation performance. In this paper, we improve the network for multi-scale feature fusion, in the medical image segmentation by introducing two feature fusion modules: i) global attention multi-scale feature fusion module (GMF); ii) local dense multi-scale feature fusion module (LMF). GMF aims to use global context information to guide the recalibration of low-level features from both spatial and channel aspects, so as to enhance the utilization of effective multi-scale features and suppress the noise of low-level features. LMF adopts bottom-up top-down structure to capture context information, to generate semantic features, and to fuse feature information at different scales. LMF can integrate local dense multi-scale context features layer by layer in the network, thus improving the ability of network to encode interdependent relationships among boundary pixels. Based on the above two modules, we propose a novel medical image segmentation framework (GLF-Net). We evaluated the proposed network and modules on challenging brain tumor segmentation and pancreas segmentation datasets, and very competitive performance has been achieved.

A multi-scale semantic feature fusion method for remote sensing crop classification

In general object detection, scale variation is always a big challenge. At present, feature pyramid networks are employed in numerous methods to alleviate the problems caused by large scale range of objects in object detection, which makes use of multi-level features extracted from the backbone for top-down upsampling and fusion to acquire a set of multi-scale depth image features. However, the feature pyramid network proposed by Ghiasi et al. adopts a simple fusion method, which fails to consider the fusion feature context, and therefore, it is difficult to acquire good features. In addition, the fusion of multi-scale features directly by traditional upsampling is prone to feature misalignment and loss of details. In this paper, an adaptive feature pyramid network is proposed based on the feature pyramid network to alleviate the foregoing potential problems, which includes two major designs, i.e., adaptive feature upsampling and adaptive feature fusion. The adaptive feature upsampling aims to predict a group of sampling points of each pixel through some models, and constitute feature representation of the pixel by feature combination of sampling points, while adaptive feature fusion is to construct pixel-level fusion weights between fusion features through attention mechanism. The experimental results verified the effectiveness of the method proposed in this paper. On the public object detection dataset MS-COCO test-dev, Faster R-CNN model achieved performance improvement of 1.2 AP by virtue of the adaptive feature pyramid network, and FCOS model could achieve performance improvement of 1.0 AP. What's more, the experiments also validated that the adaptive feature pyramid network proposed herein was more accurate for object localization.

With special consideration for complex scenes and densely distributed small objects, this frequently leads to serious false and missed detections for unmanned aerial vehicle (UAV) images in small object detection scenarios. Consequently, we propose a UAV image small object detection algorithm, termed SMA-YOLO. Firstly, a parameter-free simple slicing convolution (SSC) module is integrated in the backbone network to slice the feature maps and enhance the features so as to effectively retain the features of small objects. Subsequently, to enhance the information exchange between upper and lower layers, we design a special multi-cross-scale feature pyramid network (M-FPN). The C2f-Hierarchical-Phantom Convolution (C2f-HPC) module in the network effectively reduces information loss by fine-grained multi-scale feature fusion. Ultimately, adaptive spatial feature fusion detection Head (ASFFDHead) introduces an additional P2 detection head to enhance the resolution of feature maps to better locate small objects. Moreover, the ASFF mechanism is employed to optimize the detection process by filtering out information conflicts during multi-scale feature fusion, thereby significantly optimizing small object detection capability. Using YOLOv8n as the baseline, SMA-YOLO is evaluated on the VisDrone2019 dataset, achieving a 7.4% improvement in mAP@0.5 and a 13.3% reduction in model parameters, and we also verified its generalization ability on VAUDT and RSOD datasets, which demonstrates the effectiveness of our approach.

Bacterial wound infection poses a major challenge in trauma care and can lead to severe complications such as sepsis and organ failure. Therefore, rapid and accurate identification of the pathogen, along with targeted intervention, is of vital importance for improving treatment outcomes and reducing risks. However, current detection methods are still constrained by procedural complexity and long processing times. In this study, a hyperspectral imaging (HSI) acquisition system for bacterial analysis and a multi-scale dual-domain feature fusion transformer (MDF2Former) were developed for classifying wound bacteria. MDF2Former integrates three modules: a multi-scale feature enhancement and fusion module that generates tokens with multi-scale discriminative representations, a spatial-spectral dual-branch attention module that strengthens joint feature modeling, and a frequency and spatial-spectral domain encoding module that captures global and local interactions among tokens through a hierarchical stacking structure, thereby enabling more efficient feature learning. Extensive experiments on our self-constructed HSI dataset of typical wound bacteria demonstrate that MDF2Former achieved outstanding performance across five metrics: Accuracy (91.94%), Precision (92.26%), Recall (91.94%), F1-score (92.01%), and Kappa coefficient (90.73%), surpassing all comparative models. These results have verified the effectiveness of combining HSI with deep learning for bacterial identification, and have highlighted its potential in assisting in the identification of bacterial species and making personalized treatment decisions for wound infections.

Object detection in remote sensing images faces the challenges of a complex background, large object size variations, and high inter-class similarity. To address these problems, we propose an adaptive adjacent layer feature fusion (AALFF) method, which is developed on the basis of RTMDet. Specifically, the AALFF method incorporates an adjacent layer feature fusion enhancement (ALFFE) module, designed to capture high-level semantic information and accurately locate object spatial positions. ALFFE also effectively preserves small objects by fusing adjacent layer features and employs involution to aggregate contextual information in a wide spatial range for object essential features extraction in complex backgrounds. Additionally, the adaptive spatial feature fusion (ASFF) module is introduced to guide the network to select and fuse the crucial features to improve the adaptability to objects with different sizes. The proposed method achieves mean average precision (mAP) values of 77.1%, 88.9%, and 95.7% on the DIOR, HRRSD, and NWPU VHR-10 datasets, respectively. Notably, our approach achieves mAP75 values of 60.8% and 79.0% on the DIOR and HRRSD datasets, respectively, surpassing the state-of-the-art performance on the DIOR dataset.

To address the problem of inaccurate representation, inadequate fusion and unsmooth results in video-based single person three-dimensional human pose estimation, a multi-scale spatial-temporal feature fusion method is proposed. Firstly, the joint, limb and upper/lower body tokens were defined in spatial domain to represent the spatial multi-scale features of human body using positional embeddings. Secondly, the spatial multi-scale feature fusion module was constructed based on self-attention mechanism and multilayer perceptron to fuse joint, limb and upper/lower body features, obtaining initial pose feature sequence. Lastly, the temporal multi-scale encoding was established for temporal feature fusion to acquire final pose feature sequence, and optimize the generation of refined three-dimensional human pose through temporal decoding. Experimental results on Human3.6M dataset show that the mean per joint position error and joint velocity errors are 33.6 and 2.4 respectively, which reduce by 2.3% and 4.0%. The proposed method can improve three-dimensional human pose estimation accuracy and generate precise and smooth results while reducing computational cost. Furthermore, experimental results on HumanEva-I dataset show that the proposed method also has a certain degree of generalization ability.

Objective To address the inefficiency and high cost of manual road inspections and the limited accuracy of existing computer vision methods, this study proposes a multi-scale road defect detection model, LTF-YOLO, based on YOLO11s. The model aims to enhance both the accuracy and robustness of automated road defect detection. Methods In the feature-extraction stage, an LMSFA module replaces the original C3k2 module in YOLO11s. This module employs a hierarchical large-kernel convolution combined with group convolution and block-concatenation strategies to achieve efficient multi-scale feature aggregation. During feature fusion, an improved SPPFMPF module introduces average pooling and channel attention branches, with learnable weights enabling adaptive fusion of multi-source features. In the detection head, the TADDH module separates classification and regression subspaces through a task-decoupling mechanism. The regression branch incorporates DyDCNv2 dynamic convolution for spatial adaptive alignment, while a confidence-guided mechanism enhances detection reliability. Results Experiments on the SVRDD dataset demonstrate that, compared with the baseline YOLO11s, LTF-YOLO improves Precision by 4.4%, rising from 70.2 to 74.6, mAP@50 by 3.3%, improving from 66.4 to 69.7, and mAP@50–95 by 3.8%, rising from 39.4 to 43.2. Cross-dataset experiments on the RDD2022 dataset further demonstrate the strong generalization ability of LTF-YOLO, with mAP@50 increasing from 47.2 to 49.2 while maintaining a lightweight architecture. The proposed model achieves more accurate identification of cracks and potholes under complex road conditions, effectively reducing missed and false detections. Conclusion Through innovations in multi-scale feature extraction, adaptive feature fusion, and task-decoupled detection head design, LTF-YOLO significantly enhances detection accuracy and robustness. The model maintains high precision while remaining lightweight, providing an efficient and scalable solution for intelligent road maintenance and traffic safety monitoring.

Synthetic aperture radar (SAR) image target recognition has important application values in security reconnaissance and disaster monitoring. However, due to speckle noise and target orientation sensitivity in SAR images, traditional spatial domain recognition methods face challenges in accuracy and robustness. To effectively address these challenges, we propose a dual-branch spatial-frequency domain fusion recognition method with cross-attention, achieving deep fusion of spatial and frequency domain features. In the spatial domain, we propose an enhanced multi-scale feature extraction module (EMFE), which adopts a multi-branch parallel structure to effectively enhance the network’s multi-scale feature representation capability. Combining frequency domain guided attention, the model focuses on key regional features in the spatial domain. In the frequency domain, we design a hybrid frequency domain transformation module (HFDT) that extracts real and imaginary features through Fourier transform to capture the global structure of the image. Meanwhile, we introduce a spatially guided frequency domain attention to enhance the discriminative capability of frequency domain features. Finally, we propose a cross-domain feature fusion (CDFF) module, which achieves bidirectional interaction and optimal fusion of spatial-frequency domain features through cross attention and adaptive feature fusion. Experimental results demonstrate that our method achieves significantly superior recognition accuracy compared to existing methods on the MSTAR dataset.

Object detection (OD) in unmanned aerial vehicle (UAV) images faces many challenges, with diverse-scale objects and small objects being particularly prominent issues. To alleviate these challenges, we propose a novel multiscale feature learning and feature fusion network under the guidance of deformable convolution. First, a deformable convolution-guided feature learning (DCGFL) block is designed in the backbone to extract more effective multiscale features. The DCGFL block leverages the adaptability of deformable convolution to the shapes and scales of objects, akin to spatial attention. Moreover, it also employs channel attention to identify important feature maps. Hence, the proposed backbone possesses the functionality of spatial attention and channel attention. Second, in the neck, we devise a simple generalized feature pyramid network (SimpleGFPN) with several deformable convolution-guided feature fusion (DCGFF) blocks to fuse multiscale features. The proposed neck has cross-layer and cross-scale pathways, facilitating effective information exchange and fusion between shallow spatial and deep semantic features. Third, the SIoU loss is used to better model the bounding box regression loss. Finally, experimental results on the VisDrone2021 and UAVDT datasets show that the proposed method outperforms the compared OD methods. In terms of mean average precision, we obtain 37.8% on VisDrone2021 and 18.5% on UAVDT.

Detection of small sea vessels in synthetic aperture radar (SAR) images has received much attention in recent years because the small vessels have weak scattering intensity and few image pixels. The existing detection network structures are not well adapted to small-scale targets, the polarimetric data are not properly utilized, and the sea–land segmentation process to remove land false alarms is time-consuming. Regarding these problems, first, a single low-level path aggregation network is designed specifically for small targets. The structure reduces false alarms at the feature level by finding suitable single-scale feature maps for detection and adding a semantic enhancement module. Second, adaptive dual-polarimetric feature fusion is proposed to filter the multichannel features acquired by dual-polarimetric decomposition to reduce feature redundancy. Third, a segmentation layer is added to the network to shield the land from false alarms. The detection and segmentation layers share the feature extraction and feature fusion modules and are jointly trained by a joint loss. Finally, polarimetric SAR detection and segmentation dataset containing small vessel detection and sea–land segmentation labels is created with reference to the LS-SSDDv1.0 dataset, and experimental results on this dataset verify the improvement of this proposed method over other typical methods.

Organic electrochemical transistors (OECTs) show abundant potential in biosensors, artificial neuromorphic systems, brain-machine interfaces, etc With the fast development of novel functional materials and new device structures, OECTs with high transconductance (gm > mS) and good cycling stabilities (> 10,000 cycles) have been developed. While stability characterization is always time-consuming, to accelerate the development and commercialization of OECTs, tools for stability prediction are urgently needed. In this paper, OECTs with good cycling stabilities are realized by minimizing the gate voltage amplitude during cycling, while a remaining useful life (RUL) prediction framework for OECTs is proposed. Specifically, OECTs based on p(g2T-T) show tremendously enhanced stability which exhibits only 46.1% on-current (ION) and 33.2% peak gm decreases after 80,000 cycles (53 min). Then, RUL prediction is proposed based on the run-to-failure (RtF) aging tests (cycling stability test of OECTs). By selecting two aging parameters (ION and peak gm) as health indicators (HI), a novel multi-scale feature fusion (MFF) method for RUL prediction is proposed, which consists of a long short-term memory (LSTM) neural network based multi-scale feature generator (MFG) module for feature extraction and an attention-based feature fusion (AFF) module for feature fusion. Consequently, richer effective information is utilized to improve the prediction performance, where the experimental results show the superiority of the proposed framework on multiple OECTs in RUL prediction tasks. Therefore, by introducing such a powerful framework for the evaluation of the lifetime of OECTs, further optimization of materials, devices, and integrated systems relevant to OECTs will be stimulated. Moreover, this tool can also be extended to other relevant bioelectronics.

ObjectiveIn computer-aided medical diagnosis, precise skin lesion segmentation is crucial for the early detection and treatment of skin cancer. However, challenges such as unclear lesion boundaries, low contrast, and varying lesion shapes make accurate segmentation a difficult task. To address these challenges, we propose DMFF-Net, a multi-scale, multi-attention feature fusion network based on DeepLabV3, designed to improve the accuracy of skin lesion segmentation.MethodsDMFF-Net integrates several advanced modules to enhance segmentation performance. The network incorporates a Global Grid Coordinate Attention Module (GGCAM), which effectively fuses spatial and channel features to capture the complex relationships between local and global information. Additionally, a Multi-Scale Depthwise Separable Dilated Convolution (MDSDC) module is employed to strengthen multi-scale feature extraction, thereby preventing resolution degradation during convolution. A Mid-High Level Feature Fusion (MHLFF) module is also introduced to refine critical feature representations and suppress irrelevant information, thereby improving segmentation accuracy.ResultsThe proposed network was evaluated on four publicly available datasets: ISIC 2016, ISIC 2017, ISIC 2018, and PH2. The results show that DMFF-Net significantly outperforms existing advanced methods. Specifically, it achieves MIoU values of 89.31%, 91.47%, and 86.93% on the ISIC 2016, ISIC 2017, and ISIC 2018 datasets, respectively. Furthermore, the network achieves accuracy values of 95.62%, 97.33%, and 94.78%, and F1 scores of 96.93%, 94.91%, and 93.61%, respectively, demonstrating its robustness and effectiveness in skin lesion segmentation.ConclusionThe DMFF-Net model, with its multi-scale feature fusion and attention mechanisms, substantially improves skin lesion segmentation by preserving crucial spatial details and improving feature representation. Its superior performance on multiple datasets highlights its potential as a powerful tool for skin lesion diagnosis and provides an important reference for future advancements in medical image segmentation.

Traditional retail checkout processes often face inefficiencies, including long wait times and human errors, which negatively impact customer satisfaction and operational efficiency. This paper proposes CAE-YOLOv11n, an advanced version of the YOLOv11n object detection model, tailored for automated product classification in retail checkout systems. By incorporating three innovative modules-Convolutional Block Attention Module (CBAM), Adaptive Spatial Feature Fusion (ASFF), and Efficient IoU (EIoU)-CAE-YOLOv11n enhances feature extraction, multi-scale feature fusion, and localization accuracy. These improvements enable the model to effectively address the challenges of recognizing diverse retail products with high precision. Evaluation results demonstrate exceptional recognition accuracy and performance, highlighting the model’s potential to streamline checkout operations, reduce errors, and improve the shopping experience. This work advances retail automation and offers a practical solution for deployment in realworld retail environments.