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

Gestalt Principles of Perception01:21

Gestalt Principles of Perception

279
Gestalt principles provide a framework for understanding how humans perceive objects as unified wholes within their context. These principles are essential in explaining the cognitive processes that make sense of complex visual stimuli by organizing them into coherent groups. One fundamental principle is proximity, which posits that objects located close to each other are perceived as a collective group. For instance, when dots are positioned near one another, the visual system interprets them...
279

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

Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion.

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

Calceolarioside B alleviates airway barrier dysfunction and inflammation via targeting P2Y<sub>6</sub>R in OVA-triggered asthma.

Biochemical pharmacology·2026
Same author

Targeting KRAS for cancer therapy.

British journal of pharmacology·2026
Same author

Genomic characterization of a large-scale chikungunya outbreak in China.

The Journal of infection·2026
Same author

Communication Delay-Based Under-Actuated MASVs Distributed Formation Tracking Control With Unknown Ocean Disturbances and Input Quantization.

IEEE transactions on cybernetics·2026
Same author

<i>Acinetobacter pengchengensis</i> sp. nov., isolated from the urban wastewater of Shenzhen, Guangdong Province, China.

International journal of systematic and evolutionary microbiology·2026

相关实验视频

Updated: Jun 7, 2025

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

1.7K

可解释性 增强物体检测变压器 具有功能解.

Wenlong Yu, Ruonan Liu, Dongyue Chen

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
    |November 12, 2024
    PubMed
    概括
    此摘要是机器生成的。

    我们为深度学习对象检测模型开发了一种新的解方法,以提高可解释性. 这种方法提高了关键应用程序中的功能学习和可解释性.

    更多相关视频

    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

    471
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    369

    相关实验视频

    Last Updated: Jun 7, 2025

    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

    1.7K
    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

    471
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    369

    科学领域:

    • 计算机视觉 计算机视觉
    • 深度学习 (Deep Learning) 是一种深度学习.
    • 人工智能的人工智能

    背景情况:

    • 可解释性对于在关键应用中部署深度学习模型至关重要.
    • 现有的物体检测模型,特别是DETR变体,存在纠的特征,阻碍了可解释性.
    • 对象检测中的回归函数有助于特征纠和减少语义覆盖.

    研究的目的:

    • 用变压器 (DETR) 模型提高端到端对象检测的可解释性.
    • 引入特征解方法,以提高模型的可解释性和性能.
    • 解决基于深度学习的对象检测中纠特征的局限性.

    主要方法:

    • 在特征学习中采用了分裂与征服的脱范式.
    • 张量单数值分解 (T-SVD) 用于生成特征基础.
    • 批量平均特征光谱惩罚 (BFSP) 损失被引入,以限制特征解和平衡语义激活.

    主要成果:

    • 拟议的可解释性增强物体检测变压器与特征解 (DETD) 模型显示了改进的物体检测性能.
    • 在两个数据集上,在各种骨干和DETR变体中观察到一致的超越性.
    • 通过特征解,Grad-CAM可视化证实了增强的特征学习可解释性.

    结论:

    • DETD模型有效地解开了特征,从而提高了对象检测的可解释性.
    • 拟议的方法提高了检测性能和特征解释性.
    • 这项工作为关键领域的更可靠和可解释的深度学习模型提供了一条途径.