Journal article · 2021 · Open access

CertainNet: Sampling-Free Uncertainty Estimation for Object Detection

Stefano Gasperini, Jan Haug, Mohammad-Ali Nikouei Mahani, Alvaro Marcos-Ramiro, Nassir Navab, Benjamin Busam, Federico Tombari

IEEE Robotics and Automation Letters, 7(2), 698–705 · Published 26 November 2021 · DOI 10.1109/lra.2021.3130976

Open PDFView at the publisherCite this paper

In brief

“CertainNet: Sampling-Free Uncertainty Estimation for Object Detection” is a 2021 journal article by Stefano Gasperini and 6 co-authors, published in IEEE Robotics and Automation Letters. OpenAlex counts 39 citations as of 22 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
39
Most cited in
2023 (15)
Field-weighted impact
1.74
References
29
Authors
7

Abstract

Estimating the uncertainty of a neural network plays a fundamental role in safety-critical settings. In perception for autonomous driving, measuring the uncertainty means providing additional calibrated information to downstream tasks, such as path planning, that can use it towards safe navigation. In this work, we propose a novel sampling-free uncertainty estimation method for object detection. We call it CertainNet, and it is the first to provide separate uncertainties for each output signal: objectness, class, location and size. To achieve this, we propose an uncertainty-aware heatmap, and exploit the neighboring bounding boxes provided by the detector at inference time. We evaluate the detection performance and the quality of the different uncertainty estimates separately, also with challenging out-of-domain samples: BDD100K and nuImages with models trained on KITTI. Additionally, we propose a new metric to evaluate location and size uncertainties. When transferring to unseen datasets, CertainNet generalizes substantially better than previous methods and an ensemble, while being real-time and providing high quality and comprehensive uncertainty estimates.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Gasperini, S., Haug, J., Mahani, M.-A. N., Marcos-Ramiro, A., Navab, N., Busam, B., & Tombari, F. (2021). CertainNet: Sampling-Free Uncertainty Estimation for Object Detection. IEEE Robotics and Automation Letters, 7(2), 698–705. https://doi.org/10.1109/lra.2021.3130976

MLA 9

Gasperini, Stefano, et al. “CertainNet: Sampling-Free Uncertainty Estimation for Object Detection.” IEEE Robotics and Automation Letters, vol. 7, no. 2, 2021, pp. 698–705. https://doi.org/10.1109/lra.2021.3130976.

Chicago

Gasperini, Stefano, Jan Haug, Mohammad-Ali Nikouei Mahani, Alvaro Marcos-Ramiro, Nassir Navab, Benjamin Busam, and Federico Tombari. 2021. “CertainNet: Sampling-Free Uncertainty Estimation for Object Detection.” IEEE Robotics and Automation Letters 7 (2): 698–705. https://doi.org/10.1109/lra.2021.3130976.

Harvard

Gasperini, S. et al. (2021) ‘CertainNet: Sampling-Free Uncertainty Estimation for Object Detection’, IEEE Robotics and Automation Letters, 7(2), pp. 698–705. doi:10.1109/lra.2021.3130976.

IEEE

S. Gasperini et al., “CertainNet: Sampling-Free Uncertainty Estimation for Object Detection,” IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 698–705, 2021, doi: 10.1109/lra.2021.3130976.

BibTeX

@article{gasperini2021certainnet,
  title     = {{CertainNet: Sampling-Free Uncertainty Estimation for Object Detection}},
  author    = {Gasperini, Stefano and Haug, Jan and Mahani, Mohammad-Ali Nikouei and Marcos-Ramiro, Alvaro and Navab, Nassir and Busam, Benjamin and Tombari, Federico},
  journal   = {IEEE Robotics and Automation Letters},
  year      = {2021},
  volume    = {7},
  number    = {2},
  pages     = {698--705},
  doi       = {10.1109/lra.2021.3130976},
  url       = {https://doi.org/10.1109/lra.2021.3130976}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202111
202244
20231515
202455
20251010
202644

Its field-weighted citation impact is 1.74: it has been cited 1.74 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 › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • uncertainty estimation
  • object detection
  • autonomous driving perception
  • out-of-domain generalization
  • real-time detection
  • KITTI
  • BDD100K

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Gasperini, S., Haug, J., Mahani, M.-A. N., Marcos-Ramiro, A., Navab, N., Busam, B., & Tombari, F. (2021). CertainNet: Sampling-Free Uncertainty Estimation for Object Detection. IEEE Robotics and Automation Letters, 7(2), 698–705. https://doi.org/10.1109/lra.2021.3130976

How many times has this paper been cited?

39 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Stefano Gasperini, Jan Haug, Mohammad-Ali Nikouei Mahani, Alvaro Marcos-Ramiro, Nassir Navab, Benjamin Busam, Federico Tombari.

What is the DOI of this paper?

10.1109/lra.2021.3130976, permanently at https://doi.org/10.1109/lra.2021.3130976. 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.