Detecting infrared UAVs on edge devices through lightweight instance segmentation. by YuZhi Chen, HaoYue Sun, Liang Tian, Ye Yang, ShenYang Wang, TianYou Wang

“…First, Efficient Adaptive Downsampling (EADown) employs dual-branch processing with grouped convolutions to preserve small-target spatial features during multi-scale fusion. Second, HeteroScale Attention Network (HSAN) implements grouped multi-scale convolutions with joint channel-spatial attention mechanisms for enhanced cross-scale feature representation. …”
Get full text

Study on Lightweight Bridge Crack Detection Algorithm Based on YOLO11 by Xuwei Dong, Jiashuo Yuan, Jinpeng Dai

“…It reduces the model’s parameters and computations whilst preserving accuracy, thereby achieving a lightweight model. …”
Get full text

Mi-DETR: For Mitosis Detection From Breast Histopathology Images an Improved DETR by Fatma Betul Kara Ardac, Pakize Erdogmus

“…In the decoder layer, unnecessary model parameters have been filtered out using a layer reduction strategy to improve model efficiency and reduce computational costs. …”
Get full text

A robust deep learning framework for multiclass skin cancer classification by Burhanettin Ozdemir, Ishak Pacal

“…To overcome these obstacles, this study proposes an innovative hybrid deep learning model that combines ConvNeXtV2 blocks and separable self-attention mechanisms, tailored to enhance feature extraction and optimize classification performance. …”
Get full text

A Method for Predicting Trajectories of Concealed Targets via a Hybrid Decomposition and State Prediction Framework by Zhengpeng Yang, Jiyan Yu, Miao Liu, Tongxing Peng, Huaiyan Wang

“…The RBMO further refines critical parameters within the ISVMD-ELM pipeline, ensuring adaptability and computational efficiency across diverse scenarios. …”
Get full text

A Transfer Learning Approach for Landslide Semantic Segmentation Based on Visual Foundation Model by Changhong Hou, Junchuan Yu, Daqing Ge, Liu Yang, Laidian Xi, Yunxuan Pang, Yi Wen

“…In addition, despite the transfer learning approach can transfer SAM feature extraction capability to the landslide segmentation task, but it will consume a lot of computational resources and training time. …”
Get full text

YOLOv8n-SSDW: A Lightweight and Accurate Model for Barnyard Grass Detection in Fields by Yan Sun, Hanrui Guo, Xiaoan Chen, Mengqi Li, Bing Fang, Yingli Cao

“…However, existing deep learning models generally suffer from high parameter counts and computational complexity, limiting their practical application in field scenarios. …”
Get full text

Improved Butterfly Optimizer-Configured Extreme Learning Machine for Fault Diagnosis by Helong Yu, Kang Yuan, Wenshu Li, Nannan Zhao, Weibin Chen, Changcheng Huang, Huiling Chen, Mingjing Wang

Get full text

AI-driven genetic algorithm-optimized lung segmentation for precision in early lung cancer diagnosis by Yahia Said, Riadh Ayachi, Mouna Afif, Taoufik Saidani, Saleh T. Alanezi, Oumaima Saidani, Ali Delham Algarni

“…The proposed model builds upon the UNET3 + architecture and integrates multi-scale feature extraction with enhanced optimization strategies to improve segmentation accuracy while significantly reducing computational complexity. …”
Get full text

ZoomHead: A Flexible and Lightweight Detection Head Structure Design for Slender Cracks by Hua Li, Fan Yang, Junzhou Huo, Qiang Gao, Shusen Deng, Chang Guo

“…The results showed that the integration of ZoomHead effectively improved the model’s detection accuracy, reduced the number of parameters and computations, and increased the FPS, achieving a good balance between detection accuracy and speed. …”
Get full text

Research on improving the ranging accuracy of ships with stereo vision through Kalman filter optimization. by Zhongbo Peng, Jie Han, Liang Tong, Lumeng Wang, Dan Liu, Shijie Sun

“…In the ship detection stage, addressing challenges such as large parameters, high computational complexity, and poor real-time performance in existing ship detection models, this paper proposes the MS-YOLOv5s ship target detection algorithm. …”
Get full text

Sequential Monte Carlo Squared for online inference in stochastic epidemic models by Dhorasso Temfack, Jason Wyse

“…This feature enables timely parameter updates and significantly enhances computational efficiency compared to standard SMC2, which requires processing all past observations. …”
Get full text

A One-Stage HMDV Algorithm Applied in Multitarget Detection in SAR Images by Lei Pang, Weihe Huang, Fengli Zhang, Yinhong Song

“…To tackle these issues, this article proposes a single-stage multi-target detection network called HMDV. First, a hybrid feature extraction module is designed to address the computational complexity caused by increased width and depth in convolutional neural networks. …”
Get full text

A Rapid Concrete Crack Detection Method Based on Improved YOLOv8 by Yongzhen Wang, Jiacong He

“…Secondly, the DBB_Bottleneck is introduced into the C2f module, combining the lightweight GE_Conv with the structurally re-parameterized Diverse Branch Block, enhancing the model’s multi-scale feature extraction capability. Furthermore, the introduction of the GF_Detect detection head significantly reduces the number of model parameters while improving detection performance. …”
Get full text

A lightweight and optimized deep learning model for detecting banana bunches and stalks in autonomous harvesting vehicles by Duc Tai Nguyen, Phuoc Bao Long Do, Doan Dang Khoa Nguyen, Wei-Chih Lin

“…Additionally, a novel C2f-fast efficient channel attention module is proposed in the backbone, significantly enhancing the model's feature extraction capabilities. Furthermore, the bidirectional feature pyramid network is introduced in the original neck network, improving feature aggregation and adaptability to varying environmental conditions. …”
Get full text

Research on dimension measurement algorithm for parcel boxes in high-speed sorting system by Ning Dai, Jingchao Chen, Xudong Hu, Yanhong Yuan

“…The high-low layer feature fusion structure and C2f-GhostCondConv are designed on the neck of the model to achieve the selective fusion of input features at different levels with small parameter number and computational amount. …”
Get full text

Multimodal Prompt-Guided Bidirectional Fusion for Referring Remote Sensing Image Segmentation by Yingjie Li, Weiqi Jin, Su Qiu, Qiyang Sun

“…Multimodal feature alignment is a key challenge in referring remote sensing image segmentation (RRSIS). …”
Get full text

Development and evaluation of deep neural networks for the classification of subtypes of renal cell carcinoma from kidney histopathology images by Amit Kumar Chanchal, Shyam Lal, Shilpa Suresh

“…Additionally, the proposed method significantly reduces the number of parameters and FLOPs, demonstrating computationally efficient with 2.71 × $$10^9$$ FLOPs & 0.2131 × $$10^6$$ parameters.…”
Get full text

Research on real-time monitoring method of mine personnel protective equipment with improved YOLOv8 by Lei ZHANG, Zhipeng SUN, Hongjing TAO, Shangkai HAO, Qianru YAN, Xiwei LI

“…Detection real-time improved to 65 f·s−1, An increase of 8.3%, In addition, the number of parameters, floating point computation and model volume are 2 M, 6.6 G and 4.4 MB respectively. …”
Get full text

Lightweight detection model for safe wear at worksites using GPD-YOLOv8 algorithm by Jian Xing, Chenglong Zhan, Jiaqiang Ma, Zibo Chao, Ying Liu

“…Firstly, this study introduces the P2 detection layer within the YOLOv8 architecture, which substantially enriches semantic feature representation. Additionally, a lightweight Ghost module is integrated to replace the original backbone of YOLOv8, thereby reducing the parameter count and computational burden. …”
Get full text