Reducing DNN Labelling Cost using Surprise Adequacy: An Industrial Case Study for Autonomous Driving

TL;DR

This paper presents a method to reduce labeling costs in autonomous driving DNN development by using Surprise Adequacy to predict model performance, enabling more efficient data collection and training decisions.

Contribution

It introduces a novel approach leveraging Surprise Adequacy to predict DNN performance without manual labeling, significantly reducing costs in industrial autonomous driving applications.

Findings

Cost savings of up to 50% in data labeling.

Negligible inaccuracy in performance prediction.

Flexible trade-offs between cost and accuracy.

Abstract

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.