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

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

Transplanted Cerebrospinal Fluid-Contacting Neurons Alleviate Spasticity Following Spinal Cord Injury in Mice.

Current stem cell research & therapy·2026

Same author

An efficient triple-domain YOLOv8 for real-time aluminum profile defect detection.

Scientific reports·2026

Same author

Multi-level information fusion for explainable diagnosis of melanoma using dermoscopic images.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Same author

Identification of defects in pure and Al/Ga-doped ZnO to improve X-ray detector performance: experimental and simulation methods.

Physical chemistry chemical physics : PCCP·2025

Same author

Selective Enrichment and Identification of Cerebrospinal Fluid-Contacting Neurons In Vitro via PKD2L1 Promoter-Driven Lentiviral System.

Bio-protocol·2025

Same author

AMPL: An adaptive meta-prompt learner for few-shot image classification.

Neural networks : the official journal of the International Neural Network Society·2025

Search research articles

相关实验视频

Updated: Jun 14, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

改进的区域提案网络,用于增强少数拍摄物体检测.

Zeyu Shangguan¹, Mohammad Rostami¹

¹Department of Computer Science, University of Southern California, 3650 McClintock Avenue, Los Angeles, 90089, CA, USA.

Neural networks : the official journal of the International Neural Network Society

|September 7, 2024

概括

本研究引入了一种新型的半监督算法,通过使用未标记的新型对象来改进少量射击对象检测 (FSOD). 该方法有效地解决了标签噪声,并增强了罕见物体的检测.

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:

深度学习对象检测需要大量的注释数据,这是昂贵和耗时的,特别是对于罕见的对象.
短拍对象检测 (FSOD) 减少了数据需求,但与新型类实例作为背景噪声出现,降低性能而斗争.

研究的目的:

在FSOD培训中开发一个半监督算法来检测和利用未标记的新型对象.
通过减轻新型类实例对基准模型的负面影响来提高FSOD性能.

主要方法:

一个层次的三元分类区域提案网络 (HTRPN) 已开发,以定位和标记未标记的新型对象.
针对区域提案网络 (RPN) 实施了改进的分层采样策略,以提高对大型物体的检测.

主要成果:

拟议的方法有效地检测和利用未标记的新型物体作为FSOD训练期间的积极样本.
对COCO和PASCAL VOC数据集的实验结果表明,与现有的最先进的FSOD方法相比,性能优越.

结论:

开发的半监督方法显著提高了几次射击对象检测能力.
该HTRPN方法提供了一个有前途的解决方案,以改善对象检测有限的注释数据和处理新型对象类.

关键词:

几次射击对象检测检测对象检测区域网络提案区域网络提案半监督学习半监督学习

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 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 14, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 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