Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
In response to the increasing demands for improved model performance and reduced energy consumption in object detection tasks relevant to autonomous driving, this research presents an advanced YOLO model, designated as ECSLIF-YOLO, which is based on the Leaky Integrate-and-Fire with Extracellular Space (ECS-LIF) framework. The primary aim of this model is to tackle the issues associated with the high energy consumption of traditional artificial neural networks (ANNs) and the suboptimal performance of existing spiking neural networks (SNNs). Empirical findings demonstrate that ECSLIF-YOLO achieves a peak mean Average Precision (mAP) of 0.917 on the BDD100K and KITTI datasets, thereby aligning with the accuracy levels of conventional ANNs while exceeding the performance of current direct-training SNN approaches without incurring additional energy costs. These findings suggest that ECSLIF-YOLO is particularly well-suited to assist the development of efficient and reliable systems for autonomous driving.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12012123 | PMC |
| http://dx.doi.org/10.1038/s41598-025-97913-4 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Exploring autonomous vehicle crash risk: system coupling effects and key causal factors.
J Safety Res
September 2025
Institute for Traffic Medicine, Daping Hospital, Army Medical University, Chongqing, China.
Introduction: The continuous progression of autonomous driving technology is propelling the automotive industry into an unprecedented era, with the intelligence and driving safety capabilities of autonomous vehicles serving as crucial benchmarks for assessing industry development. However, crashes involving autonomous vehicles have raised concerns among both government authorities and the general public regarding this technology. Consequently, conducting a comprehensive analysis of crash causes and key causal factors holds immense significance for technological progress, personnel safety, and shaping the future direction of the automotive industry.
View Article and Find Full Text PDFInteractive Risk (IR): An omnidirectional safety metric of CAVs based on multimodal trajectory prediction and driving risk field.
Accid Anal Prev
September 2025
School of Vehicle and Mobility, Tsinghua University, 100084 Beijing, China. Electronic address:
Traffic accidents pose a significant threat to human life and property, and with the increasing presence of connected and autonomous vehicles (CAVs), effective risk assessment has become more critical. Current safety metrics, often limited to longitudinal or lateral assessments, fail to address omnidirectional risks or account for the uncertainties associated with vehicle intentions. This paper introduces a new omnidirectional safety metric, Interactive Risk (IR), which combines the concept of the driving risk field with multimodal trajectory prediction.
View Article and Find Full Text PDFEmergent Self-Propulsion of Skyrmionic Matter in Synthetic Antiferromagnets.
Phys Rev Lett
August 2025
Universidade Federal de Pernambuco, Núcleo de Tecnologia, Centro Acadêmico do Agreste, Avenida Marielle Franco, Caruaru-PE, 55014-900, Brazil.
Self-propulsion plays a crucial role in biological processes and nanorobotics, enabling small systems to move autonomously in noisy environments. Here, we theoretically demonstrate that a bound skyrmion-skyrmion pair in a synthetic antiferromagnetic bilayer can function as a self-propelled topological object, reaching speeds of up to a hundred million body lengths per second-far exceeding those of any known synthetic or biological self-propelled particles. The propulsion mechanism is triggered by the excitation of back-and-forth relative motion of the skyrmions, which generates nonreciprocal gyrotropic forces, driving the skyrmion pair in a direction perpendicular to their bond.
View Article and Find Full Text PDFReplication stress-induced nuclear hypertrophy alters chromatin topology and impacts cancer cell fitness.
Proc Natl Acad Sci U S A
September 2025
Graduate School of Medical Science and Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34051, Republic of Korea.
Microscopic examination of biopsy tissues remains essential for cancer diagnosis, despite advancements in sequencing technologies. Alterations in nuclear size or the nuclear-to-cytoplasmic ratio are hallmark features of cancer cells and often correlate with disease progression. However, the mechanisms underlying nuclear size abnormalities and their impact on tumor progression remain unclear.
View Article and Find Full Text PDFRegion-guided attack on the segment anything model.
Neural Netw
September 2025
School of Electronic Science and Engineering, Nanjing University, China. Electronic address:
The Segment Anything Model (SAM) is a cornerstone of image segmentation, demonstrating exceptional performance across various applications, particularly in autonomous driving and medical imaging, where precise segmentation is crucial. However, SAM is vulnerable to adversarial attacks that can significantly impair its functionality through minor input perturbations. Traditional techniques, such as FGSM and PGD, are often ineffective in segmentation tasks due to their reliance on global perturbations that overlook spatial nuances.
View Article and Find Full Text PDF