Simultaneous Learning Knowledge Distillation for Image Restoration: Efficient Model Compression for Drones by Yongheng Zhang

“…This dual-teacher approach enables the student model to learn from both degraded and clean images simultaneously, achieving robust image restoration while significantly reducing computational complexity. Experimental evaluations across five benchmark datasets and three restoration tasks—deraining, deblurring, and dehazing—demonstrate that, compared to the teacher models, the SLKD student models achieve an average reduction of 85.4% in FLOPs and 85.8% in model parameters, with only a slight average decrease of 2.6% in PSNR and 0.9% in SSIM. …”
Get full text

ResTreeNet: A Height-Aware LiDAR Tree Classification Model With Explainable AI for Forestry Applications by Asrat Kaleab Taye, Jeong-Mook Park, Hyung-Ju Cho, Jin-Taek Kang, Yeon-Ok Seo

“…With its lightweight architecture (requiring only 0.47 million parameters) and computational efficiency, ResTreeNet is a practical solution for large-scale ecological research, offering an innovative approach to automated forest monitoring and sustainable resource management.…”
Get full text

A Dual-Branch Residual Network with Attention Mechanisms for Enhanced Classification of Vaginal Lesions in Colposcopic Images by Haima Yang, Yeye Song, Yuling Li, Zubei Hong, Jin Liu, Jun Li, Dawei Zhang, Le Fu, Jinyu Lu, Lihua Qiu

Get full text

Benchmarking 21 Open-Source Large Language Models for Phishing Link Detection with Prompt Engineering by Arbi Haza Nasution, Winda Monika, Aytug Onan, Yohei Murakami

“…Additionally, our analysis highlights smaller models (7B–27B parameters) offering strong performance with substantially reduced computational costs. …”
Get full text

LCAT: A Lightweight Color-Aware Transformer With Hierarchical Attention for Leaf Disease Classification in Precision Agriculture by Parkpoom Chaisiriprasert, Khachonkit Chuiad

“…We introduce the Lightweight Color-Aware Transformer (LCAT), a model designed to achieve high accuracy and computational efficiency for practical deployment, particularly in environments with limited hardware resources. …”
Get full text

A Lightweight Two-Step Detection Method for Real-Time Small UAV Detection by Sungkyu Jung, Jaeyeon Jang, Chang Ouk Kim

“…Additionally, our compression approach preserves critical UAV features by selectively removing low-importance parameters, significantly reducing the degree of redundancy while minimizing the induced detection performance loss.…”
Get full text

A Comparative Analysis of Convolutional Neural Network (CNN): MobileNetV2 and Xception for Butterfly Species Classification by Mehta Pradnyatama, Christy Atika Sari, Eko Hari Rachmawanto, Hussain Md Mehedul Islam

“…Despite minimal performance difference, MobileNetV2 offers significant computational efficiency advantages with 4.15M parameters compared to Xception's 25.27M, while Xception provides marginally better classification. …”
Get full text

Intelligent deep learning-based dual-task approach for robust power quality event classification by Lipsa Ray, Pampa Sinha, Siddhanta Pani, Anshuman Nayak, Kaushik Paul, Chitralekha Jena, Md. Minarul Islam, Taha Selim Ustun

“…The methodology integrates the tunable-Q wavelet transform (TQWT) for signal decomposition, optimizing Q-factor parameters to extract precise features, and morphological component analysis (MCA) with the Split Augmented Lagrangian Shrinkage Algorithm (SALSA) for effective component separation. …”
Get full text

Spatio-temporal activity patterns induced by triadic interactions in an in silico neural medium by Ana P Millán, Hanlin Sun, Joaquín J Torres

Get full text

A Lightweight CNN for Multi-Class Classification of Handwritten Digits and Mathematical Symbols by Nicholas Abisha, Tita Putri Redytadevi, Sri Nurdiati, Elis Khatizah, Mohamad Khoirun Najib

“…The proposed model, implemented in Julia using the Flux.jl library, features a compact architecture with only two convolutional layers and approximately 55,000 trainable parameters significantly smaller than typical deep CNNs. …”
Get full text

EcoDetect-YOLOv2: A High-Performance Model for Multi-Scale Waste Detection in Complex Surveillance Environments by Jing Su, Ruihan Chen, Mingzhi Li, Shenlin Liu, Guobao Xu, Zanhong Zheng

“…Experiments conducted on the IEWED dataset, which features multi-object, multi-class, and highly complex real-world scenes, demonstrate that EcoDetect-YOLOv2 outperforms the baseline YOLOv8s by 1.0%, 4.6%, 4.8%, and 3.1% in precision, recall, mAP<sub data-eusoft-scrollable-element="1">50</sub>, and mAP<sub data-eusoft-scrollable-element="1">50:95</sub>, respectively, while reducing the parameter count by 19.3%. …”
Get full text

DC-WUnet: An Underwater Ranging Signal Enhancement Network Optimized with Depthwise Separable Convolution and Conformer by Xiaosen Liu, Juan Li, Jingyao Zhang, Yajie Bai, Zhaowei Cui

“…The encoder incorporates the Conformer module and skip connections to enhance the network’s multiscale feature extraction capability. Meanwhile, the network introduces depthwise separable convolution to reduce the number of parameters and improve computational efficiency. …”
Get full text

Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach by G. Mutreja, K. Bittner

“…To address this challenge, this paper investigates the effectiveness of selfsupervised learning with EfficientNet architectures, known for their computational efficiency, for building roof type classification. …”
Get full text

LE-YOLOv5: A Lightweight and Efficient Neural Network for Steel Surface Defect Detection by Chengshun Zhu, Yong Sun, Hongji Zhang, Shilong Yuan, Hui Zhang

“…Therefore, based on the industrial scenario of low computational force, this study proposed a lightweight and efficient defect detector called LE-YOLOv5. …”
Get full text

RepVGG-MEM: A Lightweight Model for Garbage Classification Achieving a Balance Between Accuracy and Speed by Qiuxin Si, Sang Ik Han

“…The backbone of this model is derived from the lightweight RepVGG architecture, augmented by the integration of a multi-scale convolutional attention module to enhance high-quality feature extraction. Experimental results demonstrate that the RepVGG-MEM model outperforms its counterparts, achieving an accuracy of 93.26%, with a parameter count of 7.2 million and a floating-point operations (FLOPs) of 1.41 billion. …”
Get full text

PHRF-RTDETR: a lightweight weed detection method for upland rice based on RT-DETR by Xianjin Jin, Jinheng Zhang, Fei Wang, Mengyan Zhao, Yunshuang Wang, Jianping Yang, Jinfeng Wu, Bing Zhou

“…Second, we integrate HiLo, a mechanism excluding parameter growth, into the AIFI module to enhance the model’s capability of capturing multi-frequency features. …”
Get full text

A Deep Learning Approach for Extracting Cyanobacterial Blooms in Eutrophic Lakes From Satellite Imagery by Nan Wang, Zhenyu Tan, Chen Yang, Jinge Ma, Hongtao Duan

“…MBAUNet was crafted as a lightweight network by integrating elements of MobileNetV3 and UNet, reducing learnable parameters and training time, while the introduction of spatial and channel attentions enhanced feature extraction. …”
Get full text

Microstrip Patch Antenna Design Using a Four-Layer Feed Forward Artificial Neural Network Trained by Levenberg-Marquardt Algorithm by Jitu Prakash Dhar, Maodudul Hasan, Eisuke Nishiyama, Ichihiko Toyoda

“…Therefore, patch antennas with three fundamental geometrical shapes can be designed using the same ANN removing computational complexity for the designers. The ANN contains a multi-layered network architecture that learns and generalizes complex patterns through the LM algorithm and weight optimization based on the datasets without any feature extraction like Deep Neural Network (DNN). …”
Get full text

WHY WE CANNOT PREDICT STRONG EARTHQUAKES IN THE EARTH’S CRUST by Iosif L. Gufeld, Margarita I. Matveeva, Oleg N. Novoselov

“…Incontrovertible achievements of the Earth sciences are reviewed, considering specific features of seismic events and variations of various parameters of the lithosphere, the block structure of the lithosphere and processes in the lithosphere. …”
Get full text

Numerical Simulation of Protective Spraying by Helicopter-Type Unmanned Aerial Vehicles by V. P. Asovsky, A. S. Kuzmenko

“…(Conclusions) The paper confirms the functionality and potential of the developed and tested computational and software system for numerical modeling of protective spraying. …”
Get full text