Systematic Testing of Convolutional Neural Networks for Autonomous Driving

Tommaso Dreossi, Shromona Ghosh, Alberto L. Sangiovanni-Vincentelli, and Sanjit A. Seshia. Systematic Testing of Convolutional Neural Networks for Autonomous Driving. In ICML Workshop on Reliable Machine Learning in the Wild (RMLW), 2017.

Download

[HTML] 

Abstract

We present a framework to systematically analyze convolutional neural networks (CNNs) used in classification of cars in autonomous vehicles. Our analysis procedure comprises an image generator that produces synthetic pictures by sampling in a lower dimension image modification subspace and a suite of visualization tools. The image generator produces images which can be used to test the CNN and hence expose its vulnerabilities. The presented framework can be used to extract insights of the CNN classifier, compare across classification models, or generate training and validation datasets.

BibTeX

@inproceedings{dreossi-rmlw17,
  author    = {Tommaso Dreossi and
               Shromona Ghosh and
               Alberto L. Sangiovanni{-}Vincentelli and
               Sanjit A. Seshia},
  title     = {Systematic Testing of Convolutional Neural Networks for Autonomous Driving},
  booktitle   = {ICML Workshop on Reliable Machine Learning in the Wild (RMLW)},
  year      = {2017},
  abstract  = {We present a framework to systematically analyze convolutional neural networks (CNNs) used in classification of cars in autonomous vehicles. Our analysis procedure comprises an image generator that produces synthetic pictures by sampling in a lower dimension image modification subspace and a suite of visualization tools. The image generator produces images which can be used to test the CNN and hence expose its vulnerabilities. The presented framework can be used to extract insights of the CNN classifier, compare across classification models, or generate training and validation datasets.},
}