arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.02622cs.CVcs.AIcs.LGstat.ML
收藏

不确定度校准及其在目标检测中的应用

Uncertainty Calibration and its Application to Object Detection

Bergische Universität Wuppertal(伍珀塔尔大学);Hochschule Ruhr West(鲁尔西应用科学大学)

Fabian Küppers

摘要:

基于图像的环境感知是驾驶员辅助系统或自动驾驶的重要组成部分。在这个范围内,现代神经网络用于识别多个对象以及单个帧内的相应位置和大小信息。这种目标检测模型的性能对于整个系统的整体性能是重要的。然而,探测模型也可能在一定程度的不确定性下预测这些物体。[...]在这项工作中,我们研究语义的不确定性(对象类型?)以及空间不确定性(对象在哪里以及它有多大?)。我们评估目标检测模型的预测不确定性是否与在真实世界数据上实现的观测误差相匹配。在这项工作的第一部分中,我们介绍了在目标检测,实例分割,和语义分割的上下文中的语义不确定性的置信度校准的定义。我们整合额外的位置信息,在我们的检查,以评估对象的位置上的语义校准属性的效果。除了测量校准之外,还可以对可能被误校准的语义不确定性执行事后重新校准。[...]这项工作的第二部分涉及的概率检测模型获得的空间不确定性。[...]我们审查和扩展常见的校准方法,使它有可能以更灵活的方式获得参数的位置信息的不确定性分布。在最后一部分中,我们展示了一个可能的用例,我们推导出的校准方法的背景下,对象跟踪。[...]我们整合了我们以前提出的校准技术,并在随后的过程中展示了语义和空间不确定性校准的实用性。[...]

英文摘要:

Image-based environment perception is an important component especially for driver assistance systems or autonomous driving. In this scope, modern neuronal networks are used to identify multiple objects as well as the according position and size information within a single frame. The performance of such an object detection model is important for the overall performance of the whole system. However, a detection model might also predict these objects under a certain degree of uncertainty. [...] In this work, we examine the semantic uncertainty (which object type?) as well as the spatial uncertainty (where is the object and how large is it?). We evaluate if the predicted uncertainties of an object detection model match with the observed error that is achieved on real-world data. In the first part of this work, we introduce the definition for confidence calibration of the semantic uncertainty in the context of object detection, instance segmentation, and semantic segmentation. We integrate additional position information in our examinations to evaluate the effect of the object's position on the semantic calibration properties. Besides measuring calibration, it is also possible to perform a post-hoc recalibration of semantic uncertainty that might have turned out to be miscalibrated. [...] The second part of this work deals with the spatial uncertainty obtained by a probabilistic detection model. [...] We review and extend common calibration methods so that it is possible to obtain parametric uncertainty distributions for the position information in a more flexible way. In the last part, we demonstrate a possible use-case for our derived calibration methods in the context of object tracking. [...] We integrate our previously proposed calibration techniques and demonstrate the usefulness of semantic and spatial uncertainty calibration in a subsequent process. [...]

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑