Conference paper · 2023 · Open access
Deep Deterministic Uncertainty: A New Simple Baseline
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 24384–24394 · Published 1 June 2023 · DOI 10.1109/cvpr52729.2023.02336
In brief
“Deep Deterministic Uncertainty: A New Simple Baseline” is a 2023 conference paper by Jishnu Mukhoti and 4 co-authors, published in IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings. OpenAlex counts 474 citations as of 22 November 2026. It is open access: the full text is free to read at Oxford University Research Archive (ORA) (University of Oxford).
- Citations
- 474
- Most cited in
- 2025 (134)
- Field-weighted impact
- 26.14
- References
- 79
- Authors
- 5
Abstract
Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive. We take two complex single-forward-pass uncertainty approaches, DUQ and SNGP, and examine whether they mainly rely on a well-regularized feature space. Crucially, without using their more complex methods for estimating uncertainty, we find that a single softmax neural net with such a regularized feature-space, achieved via residual connections and spectral normalization, outperforms DUQ and SNGP's epistemic uncertainty predictions using simple Gaussian Discriminant Analysis post-training as a separate feature-space density estimator-without fine-tuning on OoD data, feature ensembling, or input pre-procressing. Our conceptually simple Deep Deterministic Uncertainty (DDU) baseline can also be used to disentangle aleatoric and epistemic uncertainty and performs as well as Deep Ensembles, the state-of-the art for uncertainty prediction, on several OoD bench-marks (CIFAR-10/100 vs SVHN/Tiny-ImageNet, ImageNet vs ImageNet-O), active learning settings across different model architectures, as well as in large scale vision tasks like semantic segmentation, while being computationally cheaper.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Mukhoti, J., Kirsch, A., van Amersfoort, J., Torr, P. H. S., & Gal, Y. (2023). Deep Deterministic Uncertainty: A New Simple Baseline. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 24384–24394. https://doi.org/10.1109/cvpr52729.2023.02336
MLA 9
Mukhoti, Jishnu, et al. “Deep Deterministic Uncertainty: A New Simple Baseline.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2023, pp. 24384–24394. https://doi.org/10.1109/cvpr52729.2023.02336.
Chicago
Mukhoti, Jishnu, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, and Yarin Gal. 2023. “Deep Deterministic Uncertainty: A New Simple Baseline.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings: 24384–24394. https://doi.org/10.1109/cvpr52729.2023.02336.
Harvard
Mukhoti, J. et al. (2023) ‘Deep Deterministic Uncertainty: A New Simple Baseline’, IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 24384–24394. doi:10.1109/cvpr52729.2023.02336.
IEEE
J. Mukhoti, A. Kirsch, J. van Amersfoort, P. H. S. Torr, and Y. Gal, “Deep Deterministic Uncertainty: A New Simple Baseline,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 24384–24394, 2023, doi: 10.1109/cvpr52729.2023.02336.
BibTeX
@inproceedings{mukhoti2023deep,
title = {{Deep Deterministic Uncertainty: A New Simple Baseline}},
author = {Mukhoti, Jishnu and Kirsch, Andreas and van Amersfoort, Joost and Torr, Philip H. S. and Gal, Yarin},
booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings},
year = {2023},
pages = {24384--24394},
doi = {10.1109/cvpr52729.2023.02336},
url = {https://doi.org/10.1109/cvpr52729.2023.02336}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2020 | 1 | |
| 2021 | 22 | |
| 2022 | 32 | |
| 2023 | 57 | |
| 2024 | 103 | |
| 2025 | 134 | |
| 2026 | 125 |
Its field-weighted citation impact is 26.14: it has been cited 26.14 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- epistemic uncertainty
- uncertainty quantification
- Gaussian discriminant analysis
- spectral normalization
- skip connections
- out-of-distribution detection
- active learning (machine learning)
- semantic segmentation
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Mukhoti, J., Kirsch, A., van Amersfoort, J., Torr, P. H. S., & Gal, Y. (2023). Deep Deterministic Uncertainty: A New Simple Baseline. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 24384–24394. https://doi.org/10.1109/cvpr52729.2023.02336
How many times has this paper been cited?
474 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Oxford University Research Archive (ORA) (University of Oxford): sign in and open the PDF from this page.
Who wrote this paper?
Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal.
What is the DOI of this paper?
10.1109/cvpr52729.2023.02336, permanently at https://doi.org/10.1109/cvpr52729.2023.02336. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.