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

Screening for insulin resistance in children with abdominal obesity: sex-specific performance of TyG index, FGIR, and VAI.

Physical activity and nutrition·2026

Same author

Lower-neck involvement and post-concurrent chemoradiotherapy response predict distant metastasis in head and neck cancer.

Radiation oncology journal·2026

Same author

Generation of Functional Oligodendrocyte Progenitor Cells Through Serial Replating of iPSC-Derived NPC Spheres.

Cells·2026

Same author

Habitual Ultra-processed Food Intake Is Associated with Gut Dysbiosis and Pro-inflammatory Metabolite Profiles in Korean Patients with IBD.

Digestive diseases and sciences·2026

Same author

Population Pharmacokinetics and Model-Informed Precision Dosing of Lenalidomide Incorporating Total and Unbound Plasma Concentrations in Renally Impaired Patients with Multiple Myeloma.

Drug design, development and therapy·2026

Same author

Advancing Small-Molecule Immunotherapy Through Polymeric Micelle Delivery.

Pharmaceutics·2026

Search research articles

相关实验视频

Updated: Sep 13, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

使用大型多模式模型生成视觉三角形增强了使用未标记数据的复合图像检索.

Young Kyun Jang¹, Donghyun Kim²

¹Meta Platforms (United States), Menlo Park, USA.

Scientific reports

|July 28, 2025

概括

这项研究引入了一种使用未标记数据的复合图像检索 (CIR) 的新方法. 视觉三角形生成器 (VDG) 创建伪三角形,以提高CIR在各种环境中的性能,实现最先进的结果.

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:

复合图像检索 (CIR) 通常依赖于带有标记的三胞胎的监督学习,这些三胞胎很难获得并限制了可扩展性.
弱监督 (零拍摄) 的CIR使用图像-标题对,但经常产生较低的准确性,不能直接应用于未标记的数据场景.
现有的CIR方法很难利用完全没有标签的数据来完成诸如半监督学习,域调整和测试时间调整等任务.

研究的目的:

将复合图像检索 (CIR) 应用扩展到半监督学习,域调整和测试时间调整,仅使用未标记的图像数据.
提出一种新的方法,克服现有的CIR方法在处理未标记数据方面的局限性.
通过从未标记的图像集合中生成有用的训练信号,提高CIR在各种环境中的性能.

主要方法:

开发了一个视觉三角形生成器 (VDG),利用一个大型语言模型来描述参考和目标图像之间的视觉差异.
训练有素的VDG生成视觉三角形的文字描述,从未标记的辅助图像数据创建伪三角形.
使用这些伪三胞胎来提高CIR模型在半监督,域调整和测试时间调整环境中的性能.

主要成果:

拟议的VDG方法显著改进了CIR现有的监督学习方法.
在已建立的复合图像检索基准上取得了最先进的结果.

更多相关视频

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

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: Sep 13, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

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

证明了该方法在扩展CIR应用程序到半监督,域调整和测试时间调整设置中的有效性.

结论:

VDG方法为使用未标记数据进行复合图像检索提供了一个可扩展和有效的解决方案.
这种方法扩大了CIR对新领域和适应场景的适用性,而无需标记三胞胎.
VDG的无模型性质允许各种CIR模型的无集成和性能提升.