Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Structural Classification of Joints01:20

Structural Classification of Joints

8.7K
Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...
8.7K
Survival Tree01:19

Survival Tree

469
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
469
Functional Classification of Joints01:09

Functional Classification of Joints

9.0K
Functional Classification of Joints
The functional classification of joints is determined by the amount of mobility between the adjacent bones. Joints are functionally classified as a synarthrosis or immobile joint, an amphiarthrosis or slightly moveable joint, or as a diarthrosis, a freely moveable joint. Fibrous and cartilaginous joints can be functionally classified as either synarthroses  or amphiarthroses, whereas all synovial joints are classified as diarthroses.
Synarthrosis
An...
9.0K
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

9.8K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
9.8K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Multi-scale modeling of electric vehicle fatal crash risk: uncovering spatial heterogeneity and infrastructure-land use coupling mechanisms.

Accident; analysis and prevention·2026
Same author

Sweet flavor compounds produced by the endophytic fungus <i>Talaromyces funiculosus</i>.

Food science and biotechnology·2025
Same author

Traffic Vibration Signal Analysis of DAS Fiber Optic Cables with Different Coupling Based on an Improved Wavelet Thresholding Method.

Sensors (Basel, Switzerland)·2023
Same author

Comparative the efficacy and acceptability of immunosuppressive agents for myasthenia gravis: A protocol for systematic review and network meta-analysis.

Medicine·2022
Same author

A Lane-Changing Decision-Making Model of Bus Entering considering Bus Priority Based on GRU Neural Network.

Computational intelligence and neuroscience·2022
Same author

Extraordinary Characteristics of One-Dimensional PT-Symmetric Ring Optical Waveguide Networks Composed of Adjustable Length Ratio Waveguides.

Nanomaterials (Basel, Switzerland)·2022

Related Experiment Video

Updated: Mar 29, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K

Weighted Copula Entropy for Structural Pruning in Long-Tailed Autonomous Driving Object Detection.

Yue Zhou1, Jihui Ma1, Honghui Dong1,2,3

  • 1School of Traffic and Transportation, Beijing Jiaotong University, No. 3 Shangyuancun, Haidian District, Beijing 100044, China.

Entropy (Basel, Switzerland)
|March 28, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a novel structural pruning framework for autonomous driving, enhancing deep learning models by prioritizing feature utility over parameter magnitude. The method significantly improves detection of rare objects while maintaining efficiency.

Keywords:
autonomous drivingelastic net regularizationlong-tailed traffic scenariosstructural pruningweighted copula entropy

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.7K

Related Experiment Videos

Last Updated: Mar 29, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.7K

Area of Science:

  • Computer Vision
  • Deep Learning
  • Machine Learning

Background:

  • Autonomous driving systems rely on deep convolutional neural networks (CNNs) for perception, facing challenges in balancing computational efficiency and robustness on resource-limited hardware.
  • Existing structural pruning methods, based on weight magnitude or geometric statistics, inadequately handle long-tailed traffic scenarios, often pruning critical filters for rare classes.

Purpose of the Study:

  • To develop a structural pruning framework that accurately assesses semantic feature utility, moving beyond simple parameter magnitude for improved robustness in autonomous driving perception.
  • To enhance the performance of CNNs in resource-constrained environments by preserving essential features for rare classes, thereby improving safety-critical applications.

Main Methods:

  • Proposed a novel structural pruning framework utilizing weighted copula entropy to evaluate feature semantic utility, decoupling feature relevance from sample abundance.
  • Integrated Elastic Net regularization for sparsity induction and an enhanced max-relevance and min-redundancy algorithm for semantic redundancy elimination.
  • Employed inverse class frequency weighting in Copula estimation to ensure preservation of discriminative features for rare classes.

Main Results:

  • Achieved nearly 50% reduction in FLOPs and parameters at a 50% pruning rate with minimal mAP@0.5 loss (0.09% for YOLOv5l, 0.14% for YOLOv8l) on the BDD100K dataset.
  • Significantly improved mean Average Precision (mAP) for the extreme tail class 'Train' from 0% to 3.84% (YOLOv5l) and 2.76% to 5.12% (YOLOv8l).
  • Demonstrated a more favorable trade-off between detection accuracy and computational efficiency compared to mainstream pruning techniques.

Conclusions:

  • The proposed weighted copula entropy-based structural pruning offers a lightweight and effective scheme for autonomous driving perception models, enhancing robustness for rare classes.
  • This work introduces a valuable information-theoretic perspective for structured network pruning, advancing the development of efficient and reliable AI systems for autonomous vehicles.