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

相关实验视频

Updated: Jul 9, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

两个阶段的行人检测模型使用一个新的分类头域泛化域名.

Daniel Schulz1,2, Claudio A Perez1,2

  • 1Department of Electrical Engineering, and Advanced Mining Technology Center, Universidad de Chile, Santiago 8370451, Chile.

Sensors (Basel, Switzerland)
|December 9, 2023
PubMed
概括

这项研究引入了一种新的深度学习行人探测器,通过使用三倍损失来集群行人特征来增强域概括. 这种新方法在具有挑战性的CityPersons基准测试中取得了最先进的结果,特别是在重型行人场景中.

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

Spatially-resolved single-cell imaging of melanoma brain metastases identifies localized immune patterns predictive of immune checkpoint blockade response.

Neuro-oncology·2026
Same author

Molecular and Immune Landscape of Recurrent and/or Distant Metastatic Squamous Cell Carcinoma of the Head and Neck: An EORTC/IMMUCAN Project.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same author

Genomic and Immune Landscape of Recurrent and/or Metastatic Squamous Cell Carcinoma of the Head and Neck Progressing on Anti-PD-1 Treatment.

Cancer immunology research·2026
Same author

<i>In vitro</i> and <i>in vivo</i> derived macrophages occupy distinct phenotypic states.

bioRxiv : the preprint server for biology·2025
Same author

Customizing AI-based screening with real-world data: Practical insights from diabetic retinopathy.

Acta ophthalmologica·2025
Same author

Multi-modal image analysis for large-scale cancer tissue studies within IMMUcan.

Cell reports methods·2025

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 深度学习方法在自动驾驶和监控等应用中显著提升了行人检测.
  • 现有的探测器在域泛化方面面临挑战,限制了它们在不同环境中的性能.

研究的目的:

  • 开发一种新的两级行人探测器,具有改进的域泛化功能.
  • 通过使用三重损失来最大限度地缩小类内距离和最大限度地缩小类间距离来增强特征表示.

主要方法:

  • 实现了一种新的定制分类头,三倍损失集成到更快的R-CNN和级R-CNN架构中.
  • 使用在ImageNet上预训练的HRNet骨干进行特征提取.
  • 采用渐进式培训管道,对逐渐接近目标领域的数据集进行微调.

主要成果:

  • 在CityPersons基准上取得了最先进的表现.
  • 获得的MR-2分数为9.9 (合理),11.0 (小) 和36.2 (严重).
  • 在重型子集上表现出色,在具有挑战性的条件下显示出强度.

结论:

  • 拟议的三重损失集成有效地改善了行人检测领域的泛化.
关键词:
域名通用化域名通用化对象检测检测对象检测对象检测通过行人检测系统检测行人.三倍损失的三倍损失.两个阶段的检测检测.

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

558
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

相关实验视频

Last Updated: Jul 9, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K
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

558
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K
  • 新型探测器架构和渐进式培训策略带来了卓越的结果,特别是在困难的场景中.