SSHFormer: Optimizing Spectral Reconstruction with a Spatial–Spectral Hybrid Transformer by Ang Gao, Yubo Dong, Danhua Liu, Anqi Li, Zhenyuan Lin, Yuyan Li

“…Reconstructing hyperspectral images (HSIs) from RGB images is an effective technique to overcome the high cost of spectrometers. Recently, Transformers have shown potential in capturing long-range dependencies for spectral reconstruction. …”
Get full text

A Novel Involution-Based Lightweight Network for Fabric Defect Detection by Zhenxia Ke, Lingjie Yu, Chao Zhi, Tao Xue, Yuming Zhang

“…However, the computation cost of convolution neural networks (CNNs)-based models is very high. …”
Get full text

A novel lightweight YOLOv8-PSS model for obstacle detection on the path of unmanned agricultural vehicles by Zhijian Chen, Yijun Fang, Jianjun Yin, Shiyu Lv, Farhan Sheikh Muhammad, Lu Liu

“…PConv significantly reduces processing load during convolution operations, enhancing the model's real-time detection performance. …”
Get full text

SCL-YOLOv11: A Lightweight Object Detection Network for Low-Illumination Environments by Shulong Zhuo, Hao Bai, Lifeng Jiang, Xiaojian Zhou, Xu Duan, Yiqun Ma, Zihan Zhou

“…In response to the challenges of reduced detection accuracy and high edge-deployment costs encountered by mainstream single-stage object detection models under low-light conditions, this paper proposes a lightweight object detection network based on YOLOv11, integrates StarNet, C3k2-Star, and a lightweight detail-enhanced convolution and shared convolutional detection head(LSDECD), so called SCL-YOLOv11 herein. …”
Get full text

HAF-YOLO: Dynamic Feature Aggregation Network for Object Detection in Remote-Sensing Images by Pengfei Zhang, Jian Liu, Jianqiang Zhang, Yiping Liu, Jiahao Shi

“…HAF-YOLO also maintained a low computational cost of 11.8 GFLOPs, outperforming other YOLO models. …”
Get full text

A recognition model for winter peach fruits based on improved ResNet and multi-scale feature fusion by Yan Li, Chunping Li, Tingting Zhu, Shurong Zhang, Li Liu, Zhanpeng Guan

“…The high efficiency of the WinterPeachNet model makes it highly adaptable in resource-constrained environments, enabling effective object detection at a relatively low computational cost.…”
Get full text

A novel pansharpening method based on cross stage partial network and transformer by Yingxia Chen, Huiqi Liu, Faming Fang

“…Abstract In remote sensing image fusion, the conventional Convolutional Neural Networks (CNNs) extract local features of the image through layered convolution, which is limited by the receptive field and struggles to capture global features. …”
Get full text

YOLO-RDM: A high accuracy and efficient algorithm for magnetic tile surface defect detection with practical applications. by Wei Niu, Cheng Lv, Enxu Zhang, Zhongbin Wei

“…By using a lightweight convolution method, we replace the traditional convolution in the original network, thereby improving the feature extraction ability of the model and achieving lightweight processing. …”
Get full text

Human activity recognition algorithm based on the spatial feature for WBAN by Chi JIN, Zhijun LI, Dayang SUN, Fengye HU

“…Traditional image-based activity recognition algorithms have some problems,such as high computational cost,numerous blind spots and easy privacy leakage.To solve the problem above,the CCLA (convolution-convolutional long short-term memory-attention) activity recognition algorithm based on the acceleration and gyroscope data was proposed.The convolutional neural network was used to extract spatial features of activity data and got the hidden time series information from the convolutional long short-term memory network.Simulating human brain selecting attention mechanism,attention-encoder was constructed to extract the spatial and temporal features at a higher level.The CCLA algorithm was tested on UCI-HAPT (university of California Irvine-smartphone-based recognition of human activities and postural transitions) public data set,and realized the classification of 12 types of activity with the accuracy of 93.27%.…”
Get full text

Ultrasound tomography enhancement by signal feature extraction with modular machine learning method. by Bartłomiej Baran, Dariusz Majerek, Piotr Szyszka, Dariusz Wójcik, Tomasz Rymarczyk

“…The proposed solution can result in a reliable and low-cost method of object detection for various industry sectors.…”
Get full text

Real-Time Lightweight Morphological Detection for Chinese Mitten Crab Origin Tracing by Xiaofei Ma, Nannan Shen, Yanhui He, Zhuo Fang, Hongyan Zhang, Yun Wang, Jinrong Duan

“…In the first stage, an improved YOLOv10n-based model is designed by incorporating omni-dimensional dynamic convolution, a SlimNeck structure, and a Lightweight Shared Convolutional Detection head, which effectively enhances the detection accuracy of crab targets under complex multi-scale environments while reducing computational cost. …”
Get full text

Evaluation of Various Free Software Options for Catphan 504 Phantom Analysis by Lorena Cunha Fernandes, Maira Ribeiro dos Santos, Leonardo Peres da Silva, Thiago Viana Miranda Lima, Rafael Figueiredo Pohlmann Simões

“…In computed tomography, image quality tests are important to guarantee a correct medical diagnosis and a better cost and benefit for the patient. Purpose: the purpose of this study is to analyse the images reconstructed with different thorax and bone convolution filters using popular free-use software in the field of medical physics, for the Catphan 504 phantom. …”
Get full text

Lightweight and efficient skeleton-based sports activity recognition with ASTM-Net. by Bin Wu, Mei Xue, Ying Jia, Ning Zhang, GuoJin Zhao, XiuPing Wang, Chunlei Zhang

“…Second, we introduce the Temporal Multi‑branch Graph convolution Module (TMGM), which employs parallel branches of channel‑reduction, dilated temporal convolutions with varied dilation rates, pooling, and pointwise convolutions to effectively model both fine‑grained and long‑range temporal dependencies. …”
Get full text

Fast real-time detection and counting of thrips in greenhouses with multi-level feature attention and fusion by Zhangzhang He, Xinyue Chen, Ying Gao, Yu Zhang, Yuheng Guo, Tong Zhai, Xiaochen Wei, Huan Li, Haipeng Zhu, Yongkun Fu, Zhiliang Zhang, Zhiliang Zhang

“…First, we propose a lightweight backbone network, PartialNeXt, which optimizes convolution layers through Partial Convolution (PConv), ensuring both network performance and reduced complexity. …”
Get full text

Distributionally Robust Day-Ahead Dispatch Optimization for Active Distribution Networks Based on Improved Conditional Generative Adversarial Network by WEI Wei, WANG Yudong, JIN Xiaolong

“…[Results] The findings demonstrate that although the day-ahead dispatch plan cost of the proposed method increases by 1.87% and 0.21% compared with the deterministic optimization （DO） and stochastic optimization （SO） methods， the integrated operation cost decreases by 5.38% and 0.46% under the worst-case scenario， respectively. …”
Get full text

A Lightweight Transformer Model for Defect Detection in Electroluminescence Images of Photovoltaic Cells by Yang Yang, Jing Zhang, Xin Shu, Lei Pan, Ming Zhang

“…Visual-based deep learning detection methods, such as Transformer and Convolutional Neural Network (CNN) models, provide a cost-effective and adaptable solution. …”
Get full text

Towards edge-collaborative, lightweight and privacy-preserving classification framework by Jinbo XIONG, Yongjie ZHOU, Renwan BI, Liang WAN, Youliang TIAN

“…Aiming at the problems of data leakage of perceptual image and computational inefficiency of privacy-preserving classification framework in edge-side computing environment, a lightweight and privacy-preserving classification framework (PPCF) was proposed to supports encryption feature extraction and classification, and achieve the goal of data transmission and computing security under the collaborative classification process of edge nodes.Firstly, a series of secure computing protocols were designed based on additive secret sharing.Furthermore, two non-collusive edge servers were used to perform secure convolution, secure batch normalization, secure activation, secure pooling and other deep neural network computing layers to realize PPCF.Theoretical and security analysis indicate that PPCF has excellent accuracy and proved to be security.Actual performance evaluation show that PPCF can achieve the same classification accuracy as plaintext environment.At the same time, compared with homomorphic encryption and multi-round iterative calculation schemes, PPCF has obvious advantages in terms of computational cost and communication overhead.…”
Get full text

LMD_YOLO: A Lightweight and Efficient Model for Pavement Defects Detection by Shuai He, Ye Yuan, Bingyang Yin

“…The model incorporates several innovations: the Diverse Branch Block enhances the detection head, improving accuracy; the mg_conv module replaces conventional convolution layers in the neck network, optimizing feature fusion without increasing computational cost; and improvements to the backbone network further enhance efficiency. …”
Get full text

Low-light image enhancement method for underground mines based on an improved Zero-DCE model by WANG Yiwei, LI Xiaoyu, WENG Zhi, BAI Fengshan

“…A Cascaded Convolution Kernel (CCK) was employed in the deep network to reduce the number of model parameters and computational cost, thereby shortening the training time. …”
Get full text

Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS by Mengyuan Zhao, Beibei Cui, Yuehao Yu, Xiaoyi Zhang, Jiaxin Xu, Fengzheng Shi, Liang Zhao

“…First, to enhance feature extraction at various levels of abstraction in the input data, this paper proposes a novel segment-wise convolution module, C2f-GB. This module performs convolution in stages on the feature map, generating more feature maps with fewer parameters and computational resources, thereby improving the model’s feature extraction capability while reducing parameter count and computational cost. …”
Get full text