Reducing DNN labelling cost using surprise adequacy: An industrial case study for autonomous driving
Paper in proceedings, 2020

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.

Deep Neural Network

Software Testing

Autonomous Driving

Author

Jinhan Kim

Korea Advanced Institute of Science and Technology (KAIST)

Jeongil Ju

Hyundai Motor Group

Robert Feldt

Chalmers, Computer Science and Engineering (Chalmers), Software Engineering (Chalmers), Software Engineering for Testing, Requirements, Innovation and Psychology

Shin Yoo

Korea Advanced Institute of Science and Technology (KAIST)

ESEC/FSE 2020 - Proceedings of the 28th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering

1466-1476

28th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2020
Virtual, Online, USA,

Subject Categories

Other Computer and Information Science

Software Engineering

Computer Systems

DOI

10.1145/3368089.3417065

More information

Latest update

12/17/2020