在铁路基础设施的真实世界分布变化下,对3D点云的少数镜头细分
Abdur R Fayjie1, Mathijs Lens1, Patrick Vandewalle1
1EAVISE, ESAT-PSI, KU Leuven, 3000 Leuven, Belgium.
Sensors (Basel, Switzerland)
|February 26, 2025
概括
少数人学习适应3D点云模型用于铁路监控,显示强烈的传感器噪声概括,但与基础设施和地理变化作斗争. 预测性不确定性估计提高了安全关键应用的可靠性.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 地理空间分析的研究.
背景情况:
- 工业铁路监控依赖于使用深度学习的3D点云细分.
- 现实世界的系统需要能够适应基础设施升级和区域差异的模型.
- 传统模型高估了绩效,原因是培训数据中没有分布变化.
研究的目的:
- 调查可适应的铁路监控的少数射击学习.
- 正式化和评估适应域内,域内外分布和跨域转移的适应性.
- 评估预测不确定性估计在量化模型可靠性的作用.
主要方法:
- 应用了对铁路监控的3D点云细分的少数镜头学习.
- 模拟了三种类型的分布变化:传感器噪声,基础设施变化和地理变化.
- 使用标准指标和预测不确定性估计评估绩效.
主要成果:
- 短暂的学习优于微调,在域内变化下保持强大的概括 (~1%的偏差).
- 在分销之外的转变下观察到显著的性能下降,特别是在新的基础设施类别下.
- 预测不确定性估计有效量化了对分布变化的敏感性.
结论:
- 近距离学习为铁路监控提供了更好的适应性,但需要仔细考虑分配转移.
- 预测不确定性对于在安全关键的铁路应用中评估模型可靠性至关重要.
- 需要进行进一步的研究,以加强对分布之外的变化进行少量学习的稳定性.
相关概念视频
01:10Design Example: Measuring Distance Between Two Points with Obstructions
23
When measuring distances in areas with physical obstructions, such as a lake in a field, surveyors must employ techniques to calculate accurate lengths without direct line measurements. One effective method is the offset technique, which allows for precise distance estimation over inaccessible stretches.In this scenario, a surveyor must measure a side of an area that crosses a lake. Since the measuring tape cannot span the lake, the surveyor begins by establishing a baseline that aligns with...
23
01:20Structural Classification of Joints
3.1K
Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...
A fibrous joint is where the adjacent bones are united by fibrous connective...
3.1K