Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Unified Temporal-Spectral-Spatial Modeling for Robust and Generalizable Motor Imagery Brain-Computer Interfaces.

Bioengineering (Basel, Switzerland)·2026
Same author

Cooperative UAV swarms for zero knowledge verification of edge generative AI using trust-aware multiagent learning.

Scientific reports·2026
Same author

Pilot study on the effect of a Meditation-Mindfulness-Positive Psychology Training program on perceived stress and mental well-being in Korean nursing students: A mixed methods analysis.

PloS one·2026
Same author

PatientEase-Domain-Aware RAG for Rehabilitation Instruction Simplification.

Bioengineering (Basel, Switzerland)·2025
Same author

A Generative Expert-Narrated Simplification Model for Enhancing Health Literacy Among the Older Population.

Bioengineering (Basel, Switzerland)·2025
Same author

From Anatomy to Genomics Using a Multi-Task Deep Learning Approach for Comprehensive Glioma Profiling.

Bioengineering (Basel, Switzerland)·2025
Same journal

Novel Parent Survey Measures Sensory Behaviors Incorporating Sensory Modality and Stimulus Intensity.

Heliyon·2026
Same journal

Expression of concern: "SQSTM1/p62 promotes the progression of gastric cancer through epithelial-mesenchymal transition" [Heliyon 10 (2024) e24409].

Heliyon·2026
Same journal

Expression of concern: "TL1A promotes metastasis and EMT process of colorectal cancer" [Heliyon 10 (2024) e24392].

Heliyon·2026
Same journal

Expression of concern: "Factors affecting timing of surgery following neoadjuvant chemoradiation for esophageal cancer" [Heliyon 9 (2023) e23212].

Heliyon·2026
Same journal

Expression of concern: "On stratified single-valued soft topogenous structures" [Heliyon 10 (2024) e27926].

Heliyon·2026
Same journal

Expression of concern: "Artifact removal and motor imagery classification in EEG using advanced algorithms and modified DNN" [Heliyon 10 (2024) e27198].

Heliyon·2026
查看所有相关文章

相关实验视频

Updated: Jun 17, 2025

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

499

通过协作知识蒸进行高效的图像分类:一种新的AlexNet修改方法.

Avazov Kuldashboy1, Sabina Umirzakova1, Sharofiddin Allaberdiev2

  • 1Department of Computer Engineering, Gachon University Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, 461-701, Republic of Korea.

Heliyon
|August 8, 2024
PubMed
概括
此摘要是机器生成的。

本研究提出了一个轻量级的图像分类模型,使用修改的AlexNet和教师-学生协作知识蒸 (TSKD). TSKD方法增强了从中级和终级教师模型层的知识转移,以在资源有限的环境中有效学习.

关键词:
图像的分类图像的分类.轻量级的模型轻量级的模型修改过的亚历克斯网络教师与学生的协作知识蒸.

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.4K

相关实验视频

Last Updated: Jun 17, 2025

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

499
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.4K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 轻量级模型对于资源有限的环境中的图像分类至关重要.
  • 传统的知识蒸方法可能无法充分利用教师模型信息.
  • 亚历克斯网架构需要优化效率.

研究的目的:

  • 引入一种创新的,轻量级的图像分类技术.
  • 通过一种新的蒸方法来增强知识的转移.
  • 在计算限制的设置中保持高精度和稳定性.

主要方法:

  • 修改了 AlexNet 架构,采用深度可分离的卷积层.
  • 教师-学生协作知识蒸 (TSKD) 为双层学习 (中间层和最后层).
  • 开发专门的损失函数,以平衡复杂性和效率.

主要成果:

  • 这种轻量级模型在图像分类任务中实现了高精度和稳定性.
  • 与传统方法相比,TSKD促进了更有效的知识转移.
  • 架构优化和专门的损失函数提高了计算效率.

结论:

  • 建议的轻量级模型与TSKD是有效的图像分类在计算约束下.
  • 深度可分离的卷积和TSKD是有效的知识传输的关键创新.
  • 这种方法为在资源有限的场景中部署高级图像分类提供了有价值的解决方案.