# I Find Your Lack of Uncertainty in Computer Vision Disturbing

arXiv: https://arxiv.org/abs/2104.08188 · HTML: https://mlsanity.com/paper/2104.08188/

## 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 (most cited first, 28 of 28)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Accurate Uncertainties for Deep Learning Using Calibrated Regression](https://mlsanity.com/paper/1807.00263/) (2018)
- [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020)
- [Human uncertainty makes classification more robust](https://mlsanity.com/paper/1908.07086/) (2019)
- [Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding](https://mlsanity.com/paper/1511.02680/) (2015)
- [Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours](https://mlsanity.com/paper/1509.06825/) (2015)
- [Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision](https://mlsanity.com/paper/1906.01620/) (2019)
- [Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution](https://mlsanity.com/paper/1608.01041/) (2016)
- [Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans](https://mlsanity.com/paper/2008.06388/) (2020)
- [Bounding Box Regression with Uncertainty for Accurate Object Detection](https://mlsanity.com/paper/1809.08545/) (2018)
- [A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving](https://mlsanity.com/paper/2011.10671/) (2020)
- [Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving](https://mlsanity.com/paper/1904.04620/) (2019)
- [Sim-to-Real Transfer for Vision-and-Language Navigation](https://mlsanity.com/paper/2011.03807/) (2020)
- [SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates](https://mlsanity.com/paper/2008.10546/) (2020)
- [BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors](https://mlsanity.com/paper/1903.03838/) (2019)
- [Reliable training and estimation of variance networks](https://mlsanity.com/paper/1906.03260/) (2019)
- [Probabilistic Object Detection: Definition and Evaluation](https://mlsanity.com/paper/1811.10800/) (2018)
- [Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network](https://mlsanity.com/paper/2003.13815/) (2020)
- [Real-time Convolutional Neural Networks for Emotion and Gender Classification](https://mlsanity.com/paper/1710.07557/) (2017)

## Built on by (most cited first, 16 of 16)

- [Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models](https://mlsanity.com/paper/2405.02917/) (2024)
- [UGainS: Uncertainty Guided Anomaly Instance Segmentation](https://mlsanity.com/paper/2308.02046/) (2023)
- [An Uncertainty-aware Loss Function for Training Neural Networks with Calibrated Predictions](https://mlsanity.com/paper/2110.03260/) (2021)
- [Know What You do Not Know: Verbalized Uncertainty Estimation Robustness on Corrupted Images in Vision-Language Models](https://mlsanity.com/paper/2504.03440/) (2025)
- [Unified Open-Vocabulary Dense Visual Prediction](https://mlsanity.com/paper/2307.08238/) (2023)
- [Object Detection as Probabilistic Set Prediction](https://mlsanity.com/paper/2203.07980/) (2022)
- [Comparison of Uncertainty Quantification with Deep Learning in Time Series Regression](https://mlsanity.com/paper/2211.06233/) (2022)
- [Bayesian Inverse Graphics for Few-Shot Concept Learning](https://mlsanity.com/paper/2409.08351/) (2024)
- [An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks](https://mlsanity.com/paper/2504.06915/) (2025)
- [Can Bayesian Neural Networks Explicitly Model Input Uncertainty?](https://mlsanity.com/paper/2501.08285/) (2025)
- [Teaching Uncertainty Quantification in Machine Learning through Use Cases](https://mlsanity.com/paper/2108.08712/) (2021)
- [High Accurate and Explainable Multi-Pill Detection Framework with Graph Neural Network-Assisted Multimodal Data Fusion](https://mlsanity.com/paper/2303.09782/) (2023)
- [Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning](https://mlsanity.com/paper/2412.14640/) (2024)
- [Bayesian Inverse Physics for Neuro-Symbolic Robot Learning](https://mlsanity.com/paper/2506.08756/) (2025)
- [Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?](https://mlsanity.com/paper/2606.31407/) (2026)
- [ByteTraX: Enhancing the ByteTrack Architecture with Optimised Thresholding](https://mlsanity.com/paper/2609.37801/) (2026)

## 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.