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

Vision01:24

Vision

48.6K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
48.6K

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

The PTPN6-THBS1 axis drives immunosuppression in renal cell carcinoma by polarizing M2 tumor-associated macrophages.

Discover oncology·2026
Same author

DEEP-GYRALNET: ENABLING MACHINE LEARNING IN GYRAL FOLDING PATTERN EXTRACTION ON CORTICAL SURFACE.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026
Same author

Contrastive multi-view representation learning for multi-camera plant phenotyping: A cotton field study.

Plant phenomics (Washington, D.C.)·2026
Same author

Comprehensive bioinformatics and experimental analysis of PPOX reveals its carcinogenic effect in clear cell renal cell carcinoma.

Translational andrology and urology·2026
Same author

Community-level modeling of gyral folding patterns for robust and anatomically informed individualized brain mapping.

NeuroImage·2026
Same author

Unveiling the Power of Multi-Modal Template Update in RGBT Tracking.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

相关实验视频

Updated: May 5, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

面具导向视觉转换器用于短时间的学习.

Yuzhong Chen, Zhenxiang Xiao, Yi Pan

    IEEE transactions on neural networks and learning systems
    |July 8, 2024
    PubMed
    概括

    通过使用一种新的面具引导视觉转换器 (MG-ViT) 增强了短暂的学习 (FSL). 这种方法有效地引导模型专注于相关的图像补丁,提高具有有限数据的任务的性能.

    更多相关视频

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    385
    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
    07:12

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

    Published on: April 11, 2025

    322

    相关实验视频

    Last Updated: May 5, 2026

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.8K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    385
    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
    07:12

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

    Published on: April 11, 2025

    322

    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:

    • 短暂的学习 (FSL) 解决了训练模型中的挑战,这些训练模型具有有限的标记数据.
    • 视觉变压器 (ViT) 是数据密集型模型,在这种模型中,FSL的传统微调可能是低效的.
    • 现有的FSL方法在对像ViT这样的大型模型的知识概括方面扎.

    研究的目的:

    • 提出一种新的面具导向视觉转换器 (MG-ViT),以实现有效和高效的短暂学习.
    • 在低数据场景中提高ViT模型的概括能力.
    • 为了提高ViT在下游任务的性能,如分类,对象检测和细分.

    主要方法:

    • 推出了面具引导视觉转换器 (MG-ViT),可以将面具应用于图像补丁.
    • 选了与任务无关的补丁,以指导ViT专注于歧视性,与任务相关的信息.
    • 集成了一种基于主动学习的样本选择方法,以实现最佳的少数拍摄样本选择.
    • 使用梯度加权类激活映射 (Grad-CAM) 来生成面罩.

    主要成果:

    • 与标准的微调相比,MG-ViT显著提高了少数射击学习任务的性能和效率.
    • 拟议的方法显示出优异的结果,而不是基于微调的总体ViT和ResNet模型.
    • MG-ViT有效地将经过预训练的模型的知识泛化,而无需额外的计算成本.

    结论:

    • MG-ViT提供了一种具体的方法来概括像ViT这样的数据密集型模型,用于少量学习.
    • 面具引导的方法提高了视觉转换器上FSL的效率和有效性.
    • 这项工作为在低数据制度中应用大规模深度学习模型提供了有价值的见解.