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 2212.07773cs.LG
收藏

目标检测神经网络中分布外检测的并行监控

Runtime Monitoring for Out-of-Distribution Detection in Object Detection Neural Networks

AUDI AG(奥迪股份公司);Technical University of Munich(慕尼黑工业大学);CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心)

Vahid Hashemi, Jan Křetínsky, Sabine Rieder, Jessica Schmidt

摘要:

在工业中使用的真实神经网络的设置中,神经网络监控提供了一种更现实和适用的替代验证。它对于检测分布外(OOD)输入特别有用,因为网络没有经过训练,可能会产生错误的结果。我们扩展了以前提出的分类网络的感知系统能够识别和定位多个对象的运行时监控方法。此外,我们分析其充分性实验上不同种类的OOD设置,记录我们的方法的整体疗效。

英文摘要:

Runtime monitoring provides a more realistic and applicable alternative to verification in the setting of real neural networks used in industry. It is particularly useful for detecting out-of-distribution (OOD) inputs, for which the network was not trained and can yield erroneous results. We extend a runtime-monitoring approach previously proposed for classification networks to perception systems capable of identification and localization of multiple objects. Furthermore, we analyze its adequacy experimentally on different kinds of OOD settings, documenting the overall efficacy of our approach.

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。

↑