VisualBackProp: Efficient visualization of CNNs for autonomous driving

Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski, Bernhard Firner, Larry J. Ackel, Urs Muller, Phil Yeres, Karol Zieba

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a new method, that we call VisualBackProp, for visualizing which sets of pixels of the input image contribute most to the predictions made by the convolutional neural network (CNN). The method heavily hinges on exploring the intuition that the feature maps contain less and less irrelevant information to the prediction decision when moving deeper into the network. The technique we propose is dedicated for CNN-based systems for steering self-driving cars and is therefore required to run in real-time. This makes the proposed visualization method a valuable debugging tool which can be easily used during both training and inference. We justify our approach with theoretical arguments and confirm that the proposed method identifies sets of input pixels, rather than individual pixels, that collaboratively contribute to the prediction. We utilize the proposed visualization tool in the NVIDIA neural-network-based end-to-end learning system for autonomous driving, known as PilotNet. We demonstrate that VisualBackProp determines which elements in the road image most influence PilotNet's steering decision and indeed captures relevant objects on the road. The empirical evaluation furthermore shows the plausibility of the proposed approach on public road video data as well as in other applications and reveals that it compares favorably to the layer-wise relevance propagation approach, i.e. it obtains similar visualization results and achieves order of magnitude speed-ups.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Robotics and Automation, ICRA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4701-4708
Number of pages8
ISBN (Electronic)9781538630815
DOIs
StatePublished - Sep 10 2018
Event2018 IEEE International Conference on Robotics and Automation, ICRA 2018 - Brisbane, Australia
Duration: May 21 2018May 25 2018

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Conference

Conference2018 IEEE International Conference on Robotics and Automation, ICRA 2018
CountryAustralia
CityBrisbane
Period5/21/185/25/18

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'VisualBackProp: Efficient visualization of CNNs for autonomous driving'. Together they form a unique fingerprint.

  • Cite this

    Bojarski, M., Choromanska, A., Choromanski, K., Firner, B., Ackel, L. J., Muller, U., Yeres, P., & Zieba, K. (2018). VisualBackProp: Efficient visualization of CNNs for autonomous driving. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018 (pp. 4701-4708). [8461053] (Proceedings - IEEE International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2018.8461053