Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Color Vision

Color Vision

Color perception begins in the retina, the light-sensitive layer at the back of the eye. Two main theories explain how colors are seen: the trichromatic theory and the opponent-process theory. The trichromatic theory, proposed by Thomas Young in 1802 and extended by Hermann von Helmholtz in 1852, suggests that color vision is based on three types of cone receptors in the retina. These cones are sensitive to different but overlapping ranges of wavelengths corresponding to red, blue, and green.

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

Recipient-derived macrophages mediate acute cardiac allograft rejection via GSDMD-induced pyroptosis mechanism.

Clinical and translational medicine·2026

Same author

Data mining and clinical observational study on the association between smoking and premature ovarian insufficiency.

Frontiers in endocrinology·2026

Same author

Recombinant RBD-based subunit vaccines incorporating high-frequency mutation sites elicit cross-immunity and robust protection against SARS-CoV-2.

Frontiers in microbiology·2026

Same author

The Growth-Decay Mechanism: A Universal Pathway for Cyclocarbon Fusion.

Inorganic chemistry·2026

Same author

High-resolution nanopore peptide sensing, profiling and sequence assembly.

Nature nanotechnology·2026

Same author

Unusual Anti-Thermoplastics and Low Thermal Expansion in 2D Metal Halide Crystals.

Advanced materials (Deerfield Beach, Fla.)·2026

Search research articles

相关实验视频

Updated: Jun 7, 2025

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

RJ-TinyViT:一个高效的视觉转换器用于红色朱虫缺陷分类.

Chengyu Hu^1,2, Jianxin Guo^3,4, Hanfei Xie^1,2

¹School of Electronic Information, Xijing University, Xi 'an, 710123, China.

Scientific reports

|November 13, 2024

概括

本研究介绍了RJ-TinyViT,一个优化的微型视觉变压器 (TinyViT),用于红色朱树表面缺陷检测. 该模型在显著降低计算负载的情况下实现了更高的准确性,增强了实际应用.

关键词:

协调注意力协调注意力深度学习是一种深度学习.红色朱果是一种红色的朱果.表面缺陷检测检测的表面缺陷检测.视觉变压器视觉变压器

更多相关视频

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

相关实验视频

Last Updated: Jun 7, 2025

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

科学领域:

计算机视觉计算机视觉
农业技术农业技术
机器学习机器学习

背景情况:

在自然生长的红中检测表面缺陷是具有挑战性的,因为缺陷的高变化率,低对比度和噪音.
现有的方法在特征提取和复杂的网络结构方面扎,限制了效率和实际使用.

研究的目的:

开发一个高效和准确的模型,用于红色朱的表面缺陷检测.
解决当前方法在特征提取和网络复杂性方面的局限性.

主要方法:

提出了一个优化的TinyVision变压器 (TinyViT),命名为RJ-TinyViT,改进了TinyViT-5m架构.
整合了改进的多核区块 (MK区块) 和移动反向瓶卷积区块 (MBConv区块) 进行增强的特征提取.
集成了协调注意 (CA) 模块,以改善对缺陷特征的关注.

主要成果:

RJ-TinyViT实现了93.38%的分类准确度,比原来的TinyViT提高了1.84%.
从原来的TinyViT网络中将浮点操作 (FLOP) 减少到58.97%和参数 (Params) 减少到39.84%.
证明了有效的模型轻量化,同时保持高精度.

结论:

RJ-TinyViT提供了一种实用的解决方案,用于检测红朱的表面缺陷,平衡准确性和效率.
优化的网络结构和集成的关注模块提高了农产品质量检查的性能.