Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/caoyunkang/GPT4V-for-Generic-Anomaly-Detection
[Arxiv] Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead.
https://github.com/caoyunkang/GPT4V-for-Generic-Anomaly-Detection
Last synced: about 2 months ago
JSON representation
[Arxiv] Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead.
- Host: GitHub
- URL: https://github.com/caoyunkang/GPT4V-for-Generic-Anomaly-Detection
- Owner: caoyunkang
- Created: 2023-11-04T13:58:44.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2023-11-24T09:11:22.000Z (about 1 year ago)
- Last Synced: 2024-08-09T13:18:48.090Z (5 months ago)
- Homepage:
- Size: 96.1 MB
- Stars: 94
- Watchers: 3
- Forks: 6
- Open Issues: 1
-
Metadata Files:
- Readme: README.MD
Awesome Lists containing this project
- StarryDivineSky - caoyunkang/GPT4V-for-Generic-Anomaly-Detection - 4V(ision),一种强大的视觉语言模型,以通用方式处理异常检测任务。我们研究了GPT-4V在多模态、多域异常检测任务中的应用,包括图像、视频、点云和时间序列数据,涉及工业、医疗、逻辑、视频、3D异常检测和定位等多个应用领域。为了提高 GPT-4V 的性能,我们加入了不同类型的附加提示,例如班级信息、人类专业知识和参考图像作为提示。根据我们的实验,GPT-4V 被证明在检测和解释零/单次异常检测中的全局和细粒度语义模式方面非常有效。这样可以准确区分正常和异常实例。总体而言,GPT-4V在通用异常检测和理解方面表现出良好的性能,从而为异常检测开辟了一条新的途径。 (对象检测、分割 / 网络服务_其他)