Journal article · 2021 · Open access

Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection

Di Feng, Zining Wang, Yiyang Zhou, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer, Masayoshi Tomizuka, Wei Zhan

IEEE Transactions on Intelligent Transportation Systems, 23(8), 9981–9994 · Published 27 July 2021 · DOI 10.1109/tits.2021.3096943

Open PDFView at the publisherCite this paper

In brief

“Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection” is a 2021 journal article by Di Feng and 7 co-authors, published in IEEE Transactions on Intelligent Transportation Systems. OpenAlex counts 44 citations as of 22 November 2026, which puts it in the top 3% of works published in 2021 by citations. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
44
Most cited in
2025 (11)
Field-weighted impact
1.59
References
60
Authors
8

Abstract

The availability of many real-world driving datasets is a key reason behind the recent progress of object detection algorithms in autonomous driving. However, there exist ambiguity or even failures in object labels due to error-prone annotation process or sensor observation noise. Current public object detection datasets only provide deterministic object labels without considering their inherent uncertainty, as does the common training process or evaluation metrics for object detectors. As a result, an in-depth evaluation among different object detection methods remains challenging, and the training process of object detectors is sub-optimal, especially in probabilistic object detection. In this work, we infer the uncertainty in bounding box labels from LiDAR point clouds based on a generative model, and define a new representation of the probabilistic bounding box through a spatial uncertainty distribution. Comprehensive experiments show that the proposed model reflects complex environmental noises in LiDAR perception and the label quality. Furthermore, we propose Jaccard IoU (JIoU) as a new evaluation metric that extends IoU by incorporating label uncertainty. We conduct an in-depth comparison among several LiDAR-based object detectors using the JIoU metric. Finally, we incorporate the proposed label uncertainty in a loss function to train a probabilistic object detector and to improve its detection accuracy. We verify our proposed methods on two public datasets (KITTI, Waymo), as well as on simulation data. Code is released athttps://github.com/ZiningWang/Inferring-Spatial-Uncertainty-in-Object-Detection.

Cite this paper

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

APA 7

Feng, D., Wang, Z., Zhou, Y., Rosenbaum, L., Timm, F., Dietmayer, K., Tomizuka, M., & Zhan, W. (2021). Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection. IEEE Transactions on Intelligent Transportation Systems, 23(8), 9981–9994. https://doi.org/10.1109/tits.2021.3096943

MLA 9

Feng, Di, et al. “Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection.” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 8, 2021, pp. 9981–9994. https://doi.org/10.1109/tits.2021.3096943.

Chicago

Feng, Di, Zining Wang, Yiyang Zhou, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer, Masayoshi Tomizuka, and Wei Zhan. 2021. “Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection.” IEEE Transactions on Intelligent Transportation Systems 23 (8): 9981–9994. https://doi.org/10.1109/tits.2021.3096943.

Harvard

Feng, D. et al. (2021) ‘Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection’, IEEE Transactions on Intelligent Transportation Systems, 23(8), pp. 9981–9994. doi:10.1109/tits.2021.3096943.

IEEE

D. Feng et al., “Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 8, pp. 9981–9994, 2021, doi: 10.1109/tits.2021.3096943.

BibTeX

@article{feng2021labels,
  title     = {{Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection}},
  author    = {Feng, Di and Wang, Zining and Zhou, Yiyang and Rosenbaum, Lars and Timm, Fabian and Dietmayer, Klaus and Tomizuka, Masayoshi and Zhan, Wei},
  journal   = {IEEE Transactions on Intelligent Transportation Systems},
  year      = {2021},
  volume    = {23},
  number    = {8},
  pages     = {9981--9994},
  doi       = {10.1109/tits.2021.3096943},
  url       = {https://doi.org/10.1109/tits.2021.3096943}
}

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

Citations by year

YearCitationsShare of the best year
202166
202255
202355
202477
20251111
20261010

Its field-weighted citation impact is 1.59: it has been cited 1.59 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

  • spatial uncertainty
  • label uncertainty
  • LiDAR point cloud
  • generative models
  • evaluation metrics
  • autonomous driving perception
  • sensor noise
  • loss function design

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?

Feng, D., Wang, Z., Zhou, Y., Rosenbaum, L., Timm, F., Dietmayer, K., Tomizuka, M., & Zhan, W. (2021). Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection. IEEE Transactions on Intelligent Transportation Systems, 23(8), 9981–9994. https://doi.org/10.1109/tits.2021.3096943

How many times has this paper been cited?

44 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?

Di Feng, Zining Wang, Yiyang Zhou, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer, Masayoshi Tomizuka, Wei Zhan.

What is the DOI of this paper?

10.1109/tits.2021.3096943, permanently at https://doi.org/10.1109/tits.2021.3096943. 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.