BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
When incorporating deep neural networks into robotic systems, a major challenge is the lack of uncertainty measures associated with their output predictions. Methods for uncertainty estimation in the output of deep object detectors (DNNs) have been proposed in recent works, but have had limited success due to 1) information loss at the detectors nonmaximum suppression (NMS) stage, and 2) failure to take into account the multitask, many-to-one nature of anchor-based object detection. To that end, we introduce BayesOD, an uncertainty estimation approach that reformulates the standard object detector inference and Non-Maximum suppression components from a Bayesian perspective. Experiments performed on four common object detection datasets show that BayesOD provides uncertainty estimates that are better correlated with the accuracy of detections, manifesting as a significant reduction of 9.77%-13.13% on the minimum Gaussian uncertainty error metric and a reduction of 1.63%-5.23% on the minimum Categorical uncertainty error metric. Code will be released at https://github.com/asharakeh/bayes-od-rc.
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
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · cited 7×
“Such reduction in performance on KITTI is noted with all methods using MC-Dropout, implying that MC-Dropout might hurt mAP performance in cases where the testing dataset is semantically different than the training dataset.”
MethodInfluentialDropout 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
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Zhou, Y., & Tuzel, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00472 · Cited by 4,813
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 · cited 1×
“Tractable approximations can be derived through Monte-Carlo integration by using ensemble methods [22] or Monte Carlo (MC) Dropout [6].”
MethodMulti-view 3D Object Detection Network for Autonomous Driving
Chen, X., Ma, H., Wan, J., Li, B., & Xia, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.691 · Cited by 3,450
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 · cited 6×
“Finally, a straightforward extension of [7] is typically used to perform joint estimation of epistemic and aleatoric uncertainty in deep object detectors [13], [23], while still employing NMS to eliminate rather than fuse information from redundant anchors.”
BackgroundMethodInfluentialSpeed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.351 · Cited by 2,743 · cited 1×
“The majority of state of the art object detectors in 2D [17] or in 3D [1], [2], [3] follow a standard algorithm, which maps a scene representation to object instances.”
BackgroundJoint 3D Proposal Generation and Object Detection from View Aggregation
Ku, J., Mozifian, M., Lee, J., Harakeh, A., & Waslander, S. L. (2018) · 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594049 · Cited by 1,697
Self-citationMackay, D. J. C. (1995) · Network Computation in Neural Systems · doi:10.1088/0954-898x/6/3/011 · Cited by 915
LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
Meyer, G. P., Laddha, A., Kee, E., Vallespi-Gonzalez, C., & Wellington, C. K. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01296 · Cited by 374
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
“To date, there have been number of studies addressed uncertainty in deep learning algorithms for various applications including but not limited to image/video retrieval [399], [400], depth estimation [401], [402], object detection [403], [404], [405], semantic segmentation and scene understanding [406], [407], [408],…”
BackgroundA Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving
Feng, D., Harakeh, A., Waslander, S. L., & Dietmayer, K. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3096854 · Cited by 316
Self-citationLUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood
Kumar, A., Marks, T. K., Mou, W., Wang, Y., Jones, M., Cherian, A., Koike-Akino, T., Liu, X., & Feng, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00826 · Cited by 165
Active Learning for Deep Object Detection via Probabilistic Modeling
Choi, J., Elezi, I., Lee, H.-J., Farabet, C., & Alvarez, J. M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01010 · Cited by 135
“In general, the predictive uncertainty is decomposed into aleatoric and epistemic uncertainty [15, 20].”
BackgroundSingle Shot MC Dropout Approximation
Brach, K., Sick, B., & Dürr, O. (2020) · arXiv · doi:10.48550/arxiv.2007.03293 · Cited by 21
Metadata
- Authors
- Harakeh, A., Smart, M., & Waslander, S. L.
- Venue
- 2020 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2020-05
- Pages
- 87-93
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2921523090
- Cited by
- 117
- References
- 12
- FWCI
- 6.73
- Type
- conference paper
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors. https://app.cochat.ai/papers/10.1109/icra40945.2020.9196544
- The paper
- Harakeh, A., Smart, M., & Waslander, S. L. (2020). BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors. 2020 IEEE International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra40945.2020.9196544
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.