使用Surprise Quarteracy降低DNN标签成本：自动驾驶行业案例研究
Reducing DNN Labelling Cost using Surprise Adequacy: An Industrial Case Study for Autonomous Driving
摘要：
深度神经网络（DNN）正在迅速被汽车行业采用，因为它们在自动驾驶所必需的任务中表现出色。对象分割就是这样一项任务：其目的是精确定位对象的边界并对识别出的对象进行分类，帮助自动驾驶汽车识别道路环境和交通状况。这项任务不仅对安全至关重要，而且开发基于DNN的对象分割模块也带来了一系列挑战，这些挑战与传统的安全关键软件开发有很大不同。所使用的开发过程包括数据汇集、标签、培训和评估的多次迭代。在这些阶段中，培训和评价是计算密集型的，而数据汇集和贴标签是手工劳动密集型的。本文展示了如何通过利用惊喜度（SA）和模型性能之间的相关性来改进基于DNN的对象分割的开发。相关性使我们能够预测输入的模型性能，而无需手动标记它们。这反过来又使我们能够理解模型性能、更有指导性的数据汇集以及关于进一步培训的明智决策。在我们的工业案例研究中，该技术可以节省高达50%的成本，而评估的不准确性可以忽略不计。此外，工程师可以根据不同的开发阶段和场景来权衡成本节约与可容忍的不准确性水平。
英文摘要：
Deep Neural Networks (DNNs) are rapidly being adopted by the automotive industry, due to their impressive performance in tasks that are essential for autonomous driving. Object segmentation is one such task: its aim is to precisely locate boundaries of objects and classify the identified objects, helping autonomous cars to recognise the road environment and the traffic situation. Not only is this task safety critical, but developing a DNN based object segmentation module presents a set of challenges that are significantly different from traditional development of safety critical software. The development process in use consists of multiple iterations of data collection, labelling, training, and evaluation. Among these stages, training and evaluation are computation intensive while data collection and labelling are manual labour intensive. This paper shows how development of DNN based object segmentation can be improved by exploiting the correlation between Surprise Adequacy (SA) and model performance. The correlation allows us to predict model performance for inputs without manually labelling them. This, in turn, enables understanding of model performance, more guided data collection, and informed decisions about further training. In our industrial case study the technique allows cost savings of up to 50% with negligible evaluation inaccuracy. Furthermore, engineers can trade off cost savings versus the tolerable level of inaccuracy depending on different development phases and scenarios.
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。
