Towards Structured Evaluation of Deep Neural Network Supervisors
Paper in proceeding, 2019

Deep Neural Networks (DNN) have improved the quality of several non-safety related products in the past years. However, before DNNs should be deployed to safety-critical applications, their robustness needs to be systematically analyzed. A common challenge for DNNs occurs when input is dissimilar to the training set, which might lead to high confidence predictions despite proper knowledge of the input. Several previous studies have proposed to complement DNNs with a supervisor that detects when inputs are outside the scope of the network. Most of these supervisors, however, are developed and tested for a selected scenario using a specific performance metric. In this work, we emphasize the need to assess and compare the performance of supervisors in a structured way. We present a framework constituted by four datasets organized in six test cases combined with seven evaluation metrics. The test cases provide varying complexity and include data from publicly available sources as well as a novel dataset consisting of images from simulated driving scenarios. The latter we plan to make publicly available. Our framework can be used to support DNN supervisor evaluation, which in turn could be used to motive development, validation, and deployment of DNNs in safety-critical applications.


Jens Henriksson


Christian Berger

University of Gothenburg

Markus Borg

RISE Research Institutes of Sweden

Lars Tornberg

AstraZeneca AB

Cristofer Englund

RISE Research Institutes of Sweden

Sankar Raman Sathyamoorthy

Qrtech AB

Stig Ursing


Proceedings - 2019 IEEE International Conference on Artificial Intelligence Testing, AITest 2019

Vol. 1
978-1-7281-0493-5 (ISBN)

2019 IEEE International Conference On Artificial Intelligence Testing (AITest)
San Francisco, USA,

Subject Categories

Software Engineering

Computer Systems

Computer Vision and Robotics (Autonomous Systems)



More information

Latest update