I Find Your Lack of Uncertainty in Computer Vision Disturbing

by   Matias Valdenegro-Toro, et al.

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.


page 1

page 6

page 7

page 8


Quantification of Uncertainty with Adversarial Models

Quantifying uncertainty is important for actionable predictions in real-...

Uncertainty Quantification in Case of Imperfect Models: A Review

Uncertainty quantification of complex technical systems is often based o...

Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentation

Deep learning based methods for automatic organ segmentation have shown ...

Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression

Uncertainty quantification is critical for deploying deep neural network...

Uncertainty Prediction for Deep Sequential Regression Using Meta Models

Generating high quality uncertainty estimates for sequential regression,...

Sample-based Uncertainty Quantification with a Single Deterministic Neural Network

Development of an accurate, flexible, and numerically efficient uncertai...

Towards Automated Melanoma Screening: Proper Computer Vision & Reliable Results

In this paper we survey, analyze and criticize current art on automated ...

Please sign up or login with your details

Forgot password? Click here to reset