相关实验视频

Updated: May 25, 2025

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

CrackCLIP: 适应视觉语言模型用于弱监督的裂分割

Fengjiao Liang¹, Qingyong Li^1,2, Haomin Yu³

¹Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing 100044, China.

Entropy (Basel, Switzerland)

|February 26, 2025

概括

本研究介绍了CrackCLIP,用于使用最小标签进行高效的裂纹细分. 这种新的方法使用语言提示与视觉语言模型来改进结构完整性评估.

科学领域:

计算机视觉计算机视觉
人工智能的人工智能
材料科学材料科学材料科学

背景情况:

弱监督的裂细分对于结构完整性评估至关重要.
像素级注释是劳动密集型的,对于现实世界的应用来说是不切实际的.
现有的方法在标签不确定性方面扎.

研究的目的:

介绍CrackCLIP,一种用于低监督裂细分的新方法.
为了利用语言提示和对比语言图像预训练 (CLIP) 模型.
为了增强语义上下文,并提高细分精度与最小的注释.

主要方法:

使用基于梯度的类激活地图来生成粗略的伪标签.
微调CLIP的冷图像编码器与线性适配器进行裂纹细分.
使用CLIP的冷文本编码器使用文本提示来提取语义特征.
将文本提示符功能与视觉补丁令牌功能进行比较,以便最终细分.

主要成果:

在基准数据集 (Crack500,CFD,DeepCrack) 上,CrackCLIP的表现优于现有的弱监管的裂细分方法.
适应的视觉语言模型显示了裂纹特征学习的强大潜力.
该框架显示了增强的性能和通用化能力.

结论:

CrackCLIP有效地解决了裂细分中的标签不确定性.
语言提示的集成显著提高了细分性能.
拟议的方法为自动化结构健康监测提供了一个有希望的方向.

关键词:

对比的语言图像预训练视觉语言模型的模型.缺乏监督的裂细分部门.

更多相关视频

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关概念视频

Vision

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.