CoChat
Sign Up
Cited by 15Adversarial Robustness in Machine LearningAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning

I Find Your Lack of Uncertainty in Computer Vision Disturbing

Open access
Valdenegro-Toro, Matias·2021·2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
DOI 10.1109/cvprw53098.2021.00139
Open this paper in CoChat — free accountOpen PDF

Abstract

Neural networks are used for many real world applications, but often they have problems estimating their own confidence. This is particularly problematic for computer vision applications aimed at making high stakes decisions with humans and their lives. In this paper we make a meta-analysis of the literature, showing that most if not all computer vision applications do not use proper epistemic uncertainty quantification, which means that these models ignore their own limitations. We describe the consequences of using models without proper uncertainty quantification, and motivate the community to adopt versions of the models they use that have proper calibrated epistemic uncertainty, in order to enable out of distribution detection. We close the paper with a summary of challenges on estimating uncertainty for computer vision applications and recommendations.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvprw53098.2021.00139

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 39

  1. [1][1] Asmaa Abbas, Mohammed M Abdelsamea, and Mohamed Medhat Gaber. Classification of covid-19 in chest xray images using detrac deep convolutional neural network. Applied Intelligence , 51(2):854-864, 2021. 5 -
  2. [2][2] Peter Anderson, Ayush Shrivastava, Joanne Truong, Arjun Majumdar, Devi Parikh, Dhruv Batra, and Stefan Lee. Simto-real transfer for vision-and-language navigation. arXiv preprint arXiv:2011.03807 , 2020. 5 - · arXiv
  3. [3][3] Octavio Arriaga, Matias Valdenegro-Toro, and Paul Pl¨ oger. Real-time convolutional neural networks for emotion and gender classification. arXiv preprint arXiv:1710.07557 , 2017. 5 - · arXiv
  4. [4][4] Emad Barsoum, Cha Zhang, Cristian Canton Ferrer, and Zhengyou Zhang. Training deep networks for facial expression recognition with crowd-sourced label distribution. In Proceedings of the 18th ACM International Conference on Multimodal Interaction , pages 279-283, 2016. 7 -
  5. [5][5] Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, and Daan Wierstra. Weight uncertainty in neural network. In International Conference on Machine Learning , pages 1613-1622. PMLR, 2015. 2 -
  6. [6][6] Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal, Lawrence D Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, et al. End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 , 2016. 5 - · arXiv
  7. [7][7] Joy Buolamwini and Timnit Gebru. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency , pages 77-91. PMLR, 2018. 1 -
  8. [8][8] Zhe Cao, Gines Hidalgo, Tomas Simon, Shih-En Wei, and Yaser Sheikh. Openpose: realtime multi-person 2d pose estimation using part affinity fields. IEEE transactions on pattern analysis and machine intelligence , 43(1):172-186, 2019. 5 -
  9. [9][9] Jiwoong Choi, Dayoung Chun, Hyun Kim, and Hyuk-Jae Lee. Gaussian yolov3: An accurate and fast object detector using localization uncertainty for autonomous driving. In Proceedings of the IEEE/CVF International Conference on Computer Vision , pages 502-511, 2019. 6 -
  10. [10][10] Leda Cosmides and John Tooby. Are humans good intuitive statisticians after all? rethinking some conclusions from the literature on judgment under uncertainty. cognition , 58(1):173, 1996. 1 -
  11. [12][12] Armen Der Kiureghian and Ove Ditlevsen. Aleatory or epistemic? does it matter? Structural safety , 31(2):105-112, 2009. 2 -
  12. [13][13] Nicki Skafte Detlefsen, Martin Jørgensen, and Søren Hauberg. Reliable training and estimation of variance net- works. In 33rd Conference on Neural Information Processing Systems , 2019. 4 -
  13. [14][14] Di Feng, Ali Harakeh, Steven Waslander, and Klaus Dietmayer. A review and comparative study on probabilistic object detection in autonomous driving. arXiv preprint arXiv:2011.10671 , 2020. 1, 2 - · arXiv
  14. [17][17] Fredrik K Gustafsson, Martin Danelljan, and Thomas B Schon. Evaluating scalable bayesian deep learning methods for robust computer vision. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops , pages 318-319, 2020. 2 -
  15. [18][18] David Hall, Feras Dayoub, John Skinner, Haoyang Zhang, Dimity Miller, Peter Corke, Gustavo Carneiro, Anelia Angelova, and Niko S¨ underhauf. Probabilistic object detection: Definition and evaluation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision , pages 1031-1040, 2020. 2 -
  16. [19][19] Ali Harakeh, Michael Smart, and Steven L Waslander. Bayesod: A bayesian approach for uncertainty estimation in deep object detectors. In 2020 IEEE International Conference on Robotics and Automation (ICRA) , pages 87-93. IEEE, 2020. 6 -
  17. [20][20] Yihui He, Chenchen Zhu, Jianren Wang, Marios Savvides, and Xiangyu Zhang. Bounding box regression with uncertainty for accurate object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages 2888-2897, 2019. 6 -
  18. [21][21] Dan Hendrycks and Kevin Gimpel. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In International Conference on Learning Representations , 2017. 2, 4 -
  19. [22][22] Marc Hildebrandt, Jan Albiez, and Frank Kirchner. Computer-based control of deep-sea manipulators. In OCEANS 2008-MTS/IEEE Kobe Techno-Ocean , pages 1-6. IEEE, 2008. 1 -
  20. [25][25] Alex Kendall, Vijay Badrinarayanan, and Roberto Cipolla. Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680 , 2015. 6 - · arXiv
  21. [26][26] Alex Kendall and Yarin Gal. What uncertainties do we need in bayesian deep learning for computer vision? arXiv preprint arXiv:1703.04977 , 2017. 4 - · arXiv
  22. [27][27] Lingkai Kong, Jimeng Sun, and Chao Zhang. Sde-net: Equipping deep neural networks with uncertainty estimates. In International Conference on Machine Learning , pages 5405-5415. PMLR, 2020. 4 -
  23. [28][28] Volodymyr Kuleshov, Nathan Fenner, and Stefano Ermon. Accurate uncertainties for deep learning using calibrated regression. In International Conference on Machine Learning , pages 2796-2804. PMLR, 2018. 3 -
  24. [29][29] Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. Simple and scalable predictive uncertainty estimation using deep ensembles. In Advances in Neural Information Processing Systems , pages 6402-6413, 2017. 2, 4 -
  25. [30][30] Antonio Loquercio, Ana I Maqueda, Carlos R Del-Blanco, and Davide Scaramuzza. Dronet: Learning to fly by driving. IEEE Robotics and Automation Letters , 3(2):10881095, 2018. 5 -
  26. [31][31] David JC MacKay. The evidence framework applied to classification networks. Neural computation , 4(5):720-736, 1992. 2, 4 -
  27. [32][32] Manuel Martin, Alina Roitberg, Monica Haurilet, Matthias Horne, Simon Reiß, Michael Voit, and Rainer Stiefelhagen. Drive&act: A multi-modal dataset for fine-grained driver behavior recognition in autonomous vehicles. In Proceedings of the IEEE/CVF International Conference on Computer Vision , pages 2801-2810, 2019. 5 -
  28. [33][33] Maryam Matin and Matias Valdenegro-Toro. Hey Human, If your Facial Emotions are Uncertain, You Should Use BNNs! In Women in Computer Vision @ ECCV , 2020. 6, 7 -
  29. [34][34] Scott Mayer McKinney, Marcin Sieniek, Varun Godbole, Jonathan Godwin, Natasha Antropova, Hutan Ashrafian, Trevor Back, Mary Chesus, Greg S Corrado, Ara Darzi, et al. International evaluation of an ai system for breast cancer screening. Nature , 577(7788):89-94, 2020. 4, 5 -
  30. [35][35] Dimity Miller, Niko S¨ underhauf, Haoyang Zhang, David Hall, and Feras Dayoub. Benchmarking sampling-based probabilistic object detectors. In CVPR Workshops , volume 3, 2019. 6 -
  31. [36][36] Mahdi Pakdaman Naeini, Gregory Cooper, and Milos Hauskrecht. Obtaining well calibrated probabilities using bayesian binning. In Proceedings of the AAAI Conference on Artificial Intelligence , volume 29, 2015. 3 -
  32. [38][38] Nuri Erkin Ocer, Gordana Kaplan, Firat Erdem, Dilek Kucuk Matci, and Ugur Avdan. Tree extraction from multi-scale uav images using mask r-cnn with fpn. Remote Sensing Letters , 11(9):847-856, 2020. 5 -
  33. [40][40] Joshua C Peterson, Ruairidh M Battleday, Thomas L Griffiths, and Olga Russakovsky. Human uncertainty makes classification more robust. In Proceedings of the IEEE/CVF International Conference on Computer Vision , pages 96179626, 2019. 7 -
  34. [41][41] Lerrel Pinto and Abhinav Gupta. Supersizing selfsupervision: Learning to grasp from 50k tries and 700 robot hours. In 2016 IEEE international conference on robotics and automation (ICRA) , pages 3406-3413. IEEE, 2016. 5 -
  35. [42][42] John Platt et al. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in large margin classifiers , 10(3):61-74, 1999. 3 -
  36. [44][44] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. Unet: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention , pages 234-241. Springer, 2015. 5 -
  37. [45][45] Florian Schroff, Dmitry Kalenichenko, and James Philbin. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition , pages 815-823, 2015. 5 -
  38. [47][47] Natasa Tagasovska and David Lopez-Paz. Single-model uncertainties for deep learning. Advances in Neural Information Processing Systems , 32:6417-6428, 2019. 4 -
  39. [48][48] Abhinav Valada, Johan Vertens, Ankit Dhall, and Wolfram Burgard. Adapnet: Adaptive semantic segmentation in adverse environmental conditions. In 2017 IEEE International Conference on Robotics and Automation (ICRA) , pages 4644-4651. IEEE, 2017. 5 -

Cited by

Sorted by citations

Authors
Valdenegro-Toro, M.
Venue
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Publisher
IEEE
Published
2021-06
Pages
1263-1272
DOI
10.1109/cvprw53098.2021.00139
OpenAlex
W3154936951
Cited by
15
References
6
Citations by year
2026: 1 · 2025: 3 · 2024: 4 · 2023: 3 · 2022: 2 · 2021: 2
FWCI
1.23
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
epistemic uncertainty quantification, confidence calibration, artificial neural networks, computer vision, out-of-distribution detection, uncertainty estimation, high-stakes decision making

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