论文标题
检测和学习语义细分中的未知数
Detecting and Learning the Unknown in Semantic Segmentation
论文作者
论文摘要
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，通常在封闭的操作域中出现的一组封闭的对象类中训练它们。但是，这与DNN被部署到自动驾驶中的开放世界假设相反。因此，DNN一定会面临他们以前从未遇到过的数据，也称为异常，这些数据极为安全地适当应对。在这项工作中，我们首先从信息理论的角度概述了有关异常的概述。接下来，我们回顾了检测语义分割中语义未知对象的研究。我们证明，对异常对象的高熵响应的训练优于其他最新方法，这与我们的理论发现一致。此外，我们研究了一种评估异常发生频率的方法，以便选择异常类型以包括在模型的语义类别中。我们证明可以以无监督的方式学习这些异常，这特别适合基于深度学习的在线应用程序。
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.
