mlsanityData to 14 Oct 2026

I Find Your Lack of Uncertainty in Computer Vision Disturbing

arXiv 2104.08188 ↗First posted 16 Apr 2021cs.CV cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 28 of its 52 references that are in the map. First posted on arXiv 16 Apr 2021.

Builds on

28 of 52 references.

References · 28

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2017On Calibration of Modern Neural Networkscited by 4,960
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  4. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  7. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  8. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  9. 2016End to End Learning for Self-Driving Carscited by 1,009
  10. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  11. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 422
  12. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
16 more
  1. 2019Human uncertainty makes classification more robustcited by 235
  2. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  3. 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 209
  4. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  5. 2016Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distributioncited by 158
  6. 2020Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scanscited by 158
  7. 2018Bounding Box Regression with Uncertainty for Accurate Object Detectioncited by 143
  8. 2020A Review and Comparative Study on Probabilistic Object Detection in Autonomous Drivingcited by 115
  9. 2019Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Drivingcited by 105
  10. 2020Sim-to-Real Transfer for Vision-and-Language Navigationcited by 89
  11. 2020SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimatescited by 75
  12. 2019BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectorscited by 68
  13. 2019Reliable training and estimation of variance networkscited by 63
  14. 2018Probabilistic Object Detection: Definition and Evaluationcited by 55
  15. 2020Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural networkcited by 43
  16. 2017Real-time Convolutional Neural Networks for Emotion and Gender Classificationcited by 24

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 3; 2024: 3; 2025: 4; 2026: 2.

16 papers.

Sort:

By area:

  1. 2024Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Modelscited by 54
  2. 2023UGainS: Uncertainty Guided Anomaly Instance Segmentationcited by 15
  3. 2021An Uncertainty-aware Loss Function for Training Neural Networks with Calibrated Predictionscited by 6
  4. 2025Know What You do Not Know: Verbalized Uncertainty Estimation Robustness on Corrupted Images in Vision-Language Modelscited by 6
  5. 2023Unified Open-Vocabulary Dense Visual Predictioncited by 4
  6. 2022Object Detection as Probabilistic Set Predictioncited by 3
  7. 2022Comparison of Uncertainty Quantification with Deep Learning in Time Series Regressioncited by 3
  8. 2024Bayesian Inverse Graphics for Few-Shot Concept Learningcited by 2
  9. 2025An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Taskscited by 2
  10. 2025Can Bayesian Neural Networks Explicitly Model Input Uncertainty?cited by 1
  11. 2021Teaching Uncertainty Quantification in Machine Learning through Use Casescited by 0
  12. 2023High Accurate and Explainable Multi-Pill Detection Framework with Graph Neural Network-Assisted Multimodal Data Fusioncited by 0
4 more
  1. 2024Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learningcited by 0
  2. 2025Bayesian Inverse Physics for Neuro-Symbolic Robot Learningcited by 0
  3. 2026Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?cited by 0
  4. 2026ByteTraX: Enhancing the ByteTrack Architecture with Optimised Thresholdingcited by 0