在弱监督下对压缩级监控异常检测的VLM进行基准比较
Kirill Borodin1, Kirill Kondrashov1, Nikita Vasiliev1
1Faculty of Information Technology, Moscow Technical University of Communication and Informatics, Moscow 111024, Russia.
Journal of imaging
|November 26, 2025
概括
紧的视觉语言模型 (VLM) 为CCTV异常检测提供了一个实用的解决方案,平衡准确性和速度. 对参数高效的微调提高了它们的可靠性和一致性,用于实时安全监控.
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:
- 闭路电视安全监控需要高精度和低延迟的异常检测.
- 监管不足对传统的异常检测方法构成挑战.
- 紧的视觉语言模型 (VLMs) 在这个领域的潜力被探索.
研究的目的:
- 调查参数效率适应的紧型VLMs对CCTV异常检测的有效性.
- 建立一个统一的评估协议,用于比较不同的VLM方法和基线.
- 为了评估检测准确度和每剪辑延迟之间的权衡.
主要方法:
- 开发了一个统一的评估协议,标准化了预处理,提示,数据集分割,指标和运行时设置.
- 紧型VLMs使用参数高效微调进行了调整.
- 性能与没有培训的VLM管道和监督较弱的基线进行了比较.
- 这些指标包括准确度,精度,回忆,F1,ROC-AUC和平均每剪辑延迟.
主要成果:
- 以参数效率适应的紧型VLM实现了与既定方法相比或超过的性能.
- 这些模型保持了具有竞争力的每剪辑延迟,这对于实时监控至关重要.
- 适应减少了即时的敏感性,导致更一致的行为.
- 证明了有利的准确性-效率权衡.
结论:
- 参数高效的微调使紧型VLM能够充当可靠的剪贴级异常探测器.
- 紧型VLM为CCTV安全监控在弱监督下提供了实用和高效的解决方案.
- 拟议的评估协议确保了评估异常检测方法的透明度和一致性.
相关概念视频
Difference from Background: Limit of Detection
8.0K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
8.0K
Detection of Gross Error: The Q Test
6.8K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
6.8K
