arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.08700cs.CVcs.LG
收藏

语义分割中未知词的检测与学习

Detecting and Learning the Unknown in Semantic Segmentation

University of Wuppertal(伍珀塔尔大学)

Robin Chan, Svenja Uhlemeyer, Matthias Rottmann, Hanno Gottschalk

摘要:

语义分割是自动驾驶中感知的关键组成部分。深度神经网络(DNN)通常用于此任务,并且它们通常在出现在封闭操作域中的对象类的封闭集合上进行训练。然而,这与DNN部署到自动驾驶中的开放世界假设形成对比。因此,DNN必须面对以前从未遇到过的数据,也称为异常,这对于正确处理非常安全。在这项工作中,我们首先从信息论的角度对异常进行了概述。接下来,我们回顾了在语义分割中检测语义未知对象的研究。我们证明了对异常物体的高熵响应的训练优于其他最近的方法,这与我们的理论研究结果一致。此外,我们研究了一种方法来评估异常的发生频率,以选择异常类型,包括到一个模型的一组语义类别。我们证明了这些异常可以以无监督的方式学习,这特别适合基于深度学习的在线应用程序。

英文摘要:

Semantic segmentation is a crucial component for perception in automated driving. Deep neural networks (DNNs) are commonly used for this task and they are usually trained on a closed set of object classes appearing in a closed operational domain. However, this is in contrast to the open world assumption in automated driving that DNNs are deployed to. Therefore, DNNs necessarily face data that they have never encountered previously, also known as anomalies, which are extremely safety-critical to properly cope with. In this work, we first give an overview about anomalies from an information-theoretic perspective. Next, we review research in detecting semantically unknown objects in semantic segmentation. We demonstrate that training for high entropy responses on anomalous objects outperforms other recent methods, which is in line with our theoretical findings. Moreover, we examine a method to assess the occurrence frequency of anomalies in order to select anomaly types to include into a model's set of semantic categories. We demonstrate that these anomalies can then be learned in an unsupervised fashion, which is particularly suitable in online applications based on deep learning.

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。

↑