The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
A General Framework for Uncertainty Estimation in Deep Learning
Open accessAbstract
Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics. Current approaches for uncertainty estimation of neural networks require changes to the network and optimization process, typically ignore prior knowledge about the data, and tend to make over-simplifying assumptions which underestimate uncertainty. To address these limitations, we propose a novel framework for uncertainty estimation. Based on Bayesian belief networks and Monte-Carlo sampling, our framework not only fully models the different sources of prediction uncertainty, but also incorporates prior data information, e.g. sensor noise. We show theoretically that this gives us the ability to capture uncertainty better than existing methods. In addition, our framework has several desirable properties: (i) it is agnostic to the network architecture and task; (ii) it does not require changes in the optimization process; (iii) it can be applied to already trained architectures. We thoroughly validate the proposed framework through extensive experiments on both computer vision and control tasks, where we outperform previous methods by up to 23% in accuracy. The video available at https://youtu.be/X7n-bRS5vSM shows qualitative results of our experiments. The project's code is available at: https://tinyurl.com/s3nygw7.
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
Dropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2016) · arXiv · doi:10.48550/arxiv.1612.01474 · Cited by 3,666
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., & Brox, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.179 · Cited by 3,152
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
Kendall, A., & Gal, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.04977 · Cited by 3,088
A practical Bayesian framework for backpropagation networks
MacKay, D. J. C. (1992) · Neural Computation · doi:10.1162/neco.1992.4.3.448 · Cited by 2,917
Aleatory or epistemic? Does it matter?
Kiureghian, A. D., & Ditlevsen, O. (2009) · Structural Safety · doi:10.1016/j.strusafe.2008.06.020 · Cited by 2,454 · cited 1×
“To improve the quality of uncertainty estimates, this work proposes to apply ideas borrowed by Bayesian inference [5] to deep learning models.”
MethodMinimum snap trajectory generation and control for quadrotors
Mellinger, D., & Kumar, V. (2011) · 2011 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2011.5980409 · Cited by 2,367
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation
Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., & Sorkine-Hornung, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.85 · Cited by 1,989
Weight Uncertainty in Neural Networks
Blundell, C., Cornebise, J., Kavukcuoglu, K., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1505.05424 · Cited by 1,342
RotorS—A Modular Gazebo MAV Simulator Framework
Furrer, F., Burri, M., Achtelik, M., & Siegwart, R. (2016) · Studies in Computational Intelligence · doi:10.1007/978-3-319-26054-9_23 · Cited by 592
Deep reinforcement learning in a handful of trials using probabilistic dynamics models
Chua, K., Calandra, R., McAllister, R., & Levine, S. (2018) · arXiv · doi:10.48550/arxiv.1805.12114 · Cited by 525
The limits and potentials of deep learning for robotics
Sünderhauf, N., Brock, O., Scheirer, W. J., Hadsell, R. T., Fox, D., Leitner, J., Upcroft, B., Abbeel, P., Burgard, W., Milford, M. J., et al. (2018) · QUT ePrints (Queensland University of Technology) · Cited by 519
DroNet: Learning to Fly by Driving
Loquercio, A., Maqueda, A. I., del-Blanco, C. R., & Scaramuzza, D. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2795643 · Cited by 514
Self-citationProbabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
Hernández-Lobato, J. M., & Adams, R. P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.05336 · Cited by 504
Faessler, M., Franchi, A., & Scaramuzza, D. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2776353 · Cited by 469
Self-citationSelf-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation
Kahn, G., Villaflor, A., Ding, B., Abbeel, P., & Levine, S. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8460655 · Cited by 308
Feng, D., Rosenbaum, L., & Dietmayer, K. (2018) · arXiv · doi:10.48550/arxiv.1804.05132 · Cited by 260
Feng, D., Rosenbaum, L., & Dietmayer, K. (2018) · 2018 21st International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2018.8569814 · Cited by 259
A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
Fraccaro, M., Kamronn, S., Paquet, U., & Winther, O. (2017) · arXiv · doi:10.48550/arxiv.1710.05741 · Cited by 229
A 64-mW DNN-Based Visual Navigation Engine for Autonomous Nano-Drones
Palossi, D., Loquercio, A., Conti, F., Flamand, E., Scaramuzza, D., & Benini, L. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2917066 · Cited by 186
Self-citationLightweight Probabilistic Deep Networks
Gast, J., & Roth, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00355 · Cited by 169
Driving Policy Transfer via Modularity and Abstraction
Müller, M., Dosovitskiy, A., Ghanem, B., & Koltun, V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.09364 · Cited by 166
Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing
Kaufmann, E., Gehrig, M., Foehn, P., Ranftl, R., Dosovitskiy, A., Koltun, V., & Scaramuzza, D. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793631 · Cited by 149
Self-citationLearning to grasp under uncertainty
Stulp, F., Theodorou, E. A., Buchli, J., & Stefan Schaal, A. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979644 · Cited by 86
Variational Learning in Nonlinear Gaussian Belief Networks
Frey, B. J., & Hinton, G. E. (1999) · Neural Computation · doi:10.1162/089976699300016872 · Cited by 77
Robust Convolutional Neural Networks under Adversarial NoisePreprint
Jin, J., Dündar, A., & Culurciello, E. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.06306 · Cited by 74
The limits and potentials of deep learning for robotics
Sünderhauf, N., Brock, O., Scheirer, W., Hadsell, R., Fox, D., Leitner, J., Upcroft, B., Abbeel, P., Burgard, W., Milford, M., et al. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364918770733 · Cited by 38 · cited 2×
“In order to fully integrate deep learning into robotics, learning systems should reliably estimate the uncertainty in their predictions [1].”
BackgroundEnsemble Bayesian Decision Making with Redundant Deep Perceptual Control Policies
Lee, K., Wang, Z., Vlahov, B., Brar, H. K., & Theodorou, E. A. (2019) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2019.00145 · Cited by 25
Cited by
A review of uncertainty quantification in deep learning: Techniques, applications and challenges
Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., Fieguth, P., Cao, X., Khosravi, A., Acharya, U. R., et al. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.05.008 · Cited by 3,111
A survey of uncertainty in deep neural networks
Gawlikowski, J., Tassi, C. R. N., Ali, M., Lee, J., Humt, M., Feng, J., Kruspe, A., Triebel, R., Jung, P., Roscher, R., et al. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10562-9 · Cited by 1,406
End-to-End Autonomous Driving: Challenges and Frontiers
Chen, L., Wu, P., Chitta, K., Jaeger, B., Geiger, A., & Li, H. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3435937 · Cited by 610
Uncertainty quantification in scientific machine learning: Methods, metrics, and comparisons
Psaros, A. F., Meng, X., Zou, Z., Guo, L., & Karniadakis, G. E. (2023) · Journal of Computational Physics · doi:10.1016/j.jcp.2022.111902 · Cited by 455
Machine learning and deep learning—A review for ecologists
Pichler, M., & Hartig, F. (2023) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.14061 · Cited by 454
Metadata
- Authors
- Loquercio, A., Segu, M., & Scaramuzza, D.
- Venue
- IEEE Robotics and Automation Letters
- Published
- 2020-04
- Volume
- 5
- Issue
- 2
- Pages
- 3153-3160
- ISSN
- 2377-3766 (ISSN-L)
- 2377-3774
- OpenAlex
- W2956805085
- Cited by
- 291
- References
- 28
- FWCI
- 14.30
- Type
- journal article
- Language
- en
- Open access
- green
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.