Systematic Testing of Convolutional Neural Networks for Autonomous Driving

08/10/2017
by   Tommaso Dreossi, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset