VisualBackProp: Efficient Visualization of CNNs for Autonomous Driving
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · cited 13×
“The method can also be interpreted as providing an approximation to partial derivatives with respect to pixels in the input image [8].”
BackgroundMethodInfluentialOn Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524 · cited 16×
“We empirically demonstrate that it is order of magnitude faster than the state-of-the-art visualization method, layerwise relevance propagation (LRP) [10], while at the same time it leads to very similar visualization results.”
BackgroundResultInfluentialStriving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
End to End Learning for Self-Driving Cars
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M., Muller, U., Zhang, J., et al. (2016) · arXiv · doi:10.48550/arxiv.1604.07316 · Cited by 3,198
Self-citationDeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
Chen, C., Seff, A., Kornhauser, A., & Xiao, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.312 · Cited by 1,876
Understanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
Evaluating the Visualization of What a Deep Neural Network Has Learned
Samek, W., Binder, A., Montavon, G., Lapuschkin, S., & Muller, K.-R. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2599820 · Cited by 1,164
Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
Zintgraf, L. M., Cohen, T. S., Adel, T., & Welling, M. (2017) · arXiv · doi:10.48550/arxiv.1702.04595 · Cited by 487 · cited 1×
“Finally, the recently published method [20] based on the prediction difference analysis [21] is a probabilistic approach that extends the idea in [14] of visualizing the probability of the correct class using the occlusion of the parts of the image.”
MethodHow to Explain Individual Classification Decisions
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1859912 · Cited by 54 · cited 3×
“Finally, sensitivity-based methods [8, 7, 9]) aim to understand how the classifier works in different parts of the input domain by computing scores based on partial derivatives at the given sample.”
BackgroundMethod
Cited by
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems
Mohseni, S., Zarei, N., & Ragan, E. D. (2021) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3387166 · Cited by 785
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems
Mohseni, S., Zarei, N., & Ragan, E. D. (2018) · arXiv · doi:10.48550/arxiv.1811.11839 · Cited by 783
“tworthiness validation include evaluating model reliability in financial risk assessment [51], model fairness in social influencing applications [196], and model safety for its intended functionality [20]. Researchers have also proposed various regularization and techniques for enhancing trustworthy feature learning i…”
Explanations in Autonomous Driving: A Survey
Omeiza, D., Webb, H., Jirotka, M., & Kunze, L. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3122865 · Cited by 355
Neural circuit policies enabling auditable autonomy
Lechner, M., Hasani, R., Amini, A., Henzinger, T. A., Rus, D., & Grosu, R. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00237-3 · Cited by 308
Recent Advancements in End-to-End Autonomous Driving Using Deep Learning: A Survey
Chib, P. S., & Singh, P. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3318070 · Cited by 301
Metadata
- Authors
- Bojarski, M., Choromanska, A., Choromanski, K., Firner, B., Ackel, L. J., Muller, U., Yeres, P., & Zieba, K.
- Venue
- 2018 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2018-05
- Pages
- 4701-4708
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2889977670
- Cited by
- 87
- References
- 10
- FWCI
- 3.85
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.