DeepAI AI Chat
Log In Sign Up

A Methodology to Identify Cognition Gaps in Visual Recognition Applications Based on Convolutional Neural Networks

by   Hannes Vietz, et al.

Developing consistently well performing visual recognition applications based on convolutional neural networks, e.g. for autonomous driving, is very challenging. One of the obstacles during the development is the opaqueness of their cognitive behaviour. A considerable amount of literature has been published which describes irrational behaviour of trained CNNs showcasing gaps in their cognition. In this paper, a methodology is presented that creates worstcase images using image augmentation techniques. If the CNN's cognitive performance on such images is weak while the augmentation techniques are supposedly harmless, a potential gap in the cognition has been found. The presented worst-case image generator is using adversarial search approaches to efficiently identify the most challenging image. This is evaluated with the well-known AlexNet CNN using images depicting a typical driving scenario.


page 5

page 6


Systematic Testing of Convolutional Neural Networks for Autonomous Driving

We present a framework to systematically analyze convolutional neural ne...

On the rate of convergence of image classifiers based on convolutional neural networks

Image classifiers based on convolutional neural networks are defined, an...

Behaviour-based Knowledge Systems: An Epigenetic Path from Behaviour to Knowledge

In this paper we expose the theoretical background underlying our curren...

Auto-calibration Method Using Stop Signs for Urban Autonomous Driving Applications

For use of cameras on an intelligent vehicle, driving over a major bump ...

Dealing with Robustness of Convolutional Neural Networks for Image Classification

SW-based systems depend more and more on AI also for critical tasks. For...

Polarimetric image augmentation

Robotics applications in urban environments are subject to obstacles tha...