相关实验视频

Updated: Jan 9, 2026

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

在预训练的医疗视觉语言模型中,用于防御对立噪音的轻量级微调方法

Xu Han¹, Linghao Jin², Xuezhe Ma²

¹Yale University.

Findings of ACL. EMNLP. Conference on Empirical Methods in Natural Language Processing

|December 2, 2025

概括

视觉语言模型 (VLMs) 对杂的医疗数据进行了微调,显示性能下降. 一个新的纠正对抗噪音 (RAN) 框架减轻了这些问题,提高了模型的稳定性和可转移性.

科学领域:

人工智能的人工智能
医疗成像医学成像
计算机视觉计算机视觉

背景情况:

视觉语言模型 (VLMs) 在医疗图像和文本任务中表现出色.
预培训数据集面临隐私问题和噪音,影响性能.
多式联网发电对敌对攻击的易感性加剧了噪音问题.

研究的目的:

使用对抗性噪音数据调查VLM在医疗任务中的表现.
分析噪音水平对VLM稳定性和可转移性的影响.
开发一种方法来防御对手的攻击,并减轻噪音.

主要方法:

使用多模式对抗性攻击制作杂的上游数据集.
在下游医疗任务上评估VLM性能.
提出了纠正对抗噪声 (RAN) 框架,以减轻噪声.

主要成果:

适度的噪音改善了VLM的稳定性和可转移性.
增加的噪音水平对下游任务性能产生了负面影响.
RAN框架有效地抵御了对抗性攻击,并纠正了噪音.

结论:

在预培训数据中的对抗性噪音对VLM在医疗应用中的重大挑战.
在杂的环境中,RAN框架为提高VLM可靠性和性能提供了一个有希望的解决方案.
对降噪策略的进一步研究对于在医疗保健领域推进人工智能至关重要.

更多相关视频

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

相关概念视频

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

Improving Translational Accuracy

Improving Translational Accuracy