Object detectors in real-world applications often fail to detect objects due
to varying factors such as weather conditions and noisy input. Therefore, a
process that mitigates false detections is crucial for both safety and
accuracy. While uncertainty-based thresholding shows promise, previous works
demonstrate an imperfect correlation between uncertainty and detection errors.
This hinders ideal thresholding, prompting us to further investigate the
correlation and associated cost with different types of uncertainty. We
therefore propose a cost-sensitive framework for object detection tailored to
user-defined budgets on the two types of errors, missing and false detections.
We derive minimum thresholding requirements to prevent performance degradation
and define metrics to assess the applicability of uncertainty for failure
recognition. Furthermore, we automate and optimize the thresholding process to
maximize the failure recognition rate w.r.t. the specified budget. Evaluation
on three autonomous driving datasets demonstrates that our approach
significantly enhances safety, particularly in challenging scenarios.
Leveraging localization aleatoric uncertainty and softmax-based entropy only,
our method boosts the failure recognition rate by 36-60\% compared to
conventional approaches. Code is available at
this https URL

为了提高对象检测的准确性和安全性，研究提出了一种基于阈值和不确定性的成本敏感的对象检测框架，用于避免错误检测。通过分析不同类型的不确定性与检测错误之间的相关性和成本，该方法自动优化阈值以最大化对指定预算的错误识别率，在自动驾驶数据集上的评估结果表明，该方法较传统方法提高了 36-60% 的错误识别率。

面向成本敏感的基于不确定性的物体检测故障识别

Cost-Sensitive Uncertainty-Based Failure Recognition for Object  Detection

Milling machines form an integral part of many industrial processing chains.
As a consequence, several machine learning based approaches for tool wear
detection have been proposed in recent years, yet these methods mostly deal
with standard milling machines, while machinery designed for more specialized
tasks has gained only limited attention so far. This paper demonstrates the
application of an acceleration sensor to allow for convenient condition
monitoring of such a special purpose machine, i.e. round seam milling machine.
We examine a variety of conditions including blade wear and blade breakage as
well as improper machine mounting or insufficient transmission belt tension. In
addition, we presents different approaches to supervised failure recognition
with limited amounts of training data. Hence, aside theoretical insights, our
analysis is of high, practical importance, since retrofitting older machines
with acceleration sensors and an on-edge classification setup comes at low cost
and effort, yet provides valuable insights into the state of the machine and
tools in particular and the production process in general.

使用加速度传感器监测特殊类型的铣削机器的状态，通过有限的训练数据提出了监测工具磨损、机器故障等问题的监测和分类方案，实现工业制造过程的成本和效率的提升。