Can Your AI Differentiate Cats from Covid-19? Sample Efficient Uncertainty Estimation for Deep Learning Safety

06/15/2020
by   Bhavya Kailkhura, et al.
0

Deep Neural Networks (DNNs) are known to make highly overconfident predictions on Out-of- Distribution data. Recent research has shown that uncertainty-aware models, such as, Bayesian Neural Network (BNNs) and Deep Ensembles, are less susceptible to this issue. However research in this area has been largely confined to the big data setting. In this work, we show that even state-of-the-art BNNs and Ensemble models tend to make overconfident predictions when the amount of training data is insufficient. This is especially concerning for emerging applications in physical sciences and healthcare where overconfident and inaccurate predictions can lead to disastrous consequences. To address the issue of accurate uncertainty (or confidence) estimation in the small-data regime, we propose a probabilistic generalization of the popular sample-efficient non-parametric kNN approach. We demonstrate the usefulness of the proposed approach on a real-world application of COVID-19 diagnosis from chest X-Rays by (a) highlighting surprising failures of existing techniques, and (b) achieving superior uncertainty quantification as compared to state-of-the-art.

READ FULL TEXT

Authors

page 1

06/17/2020

Sample Efficient Uncertainty Estimation for Deep Learning Safety

Deep Neural Networks (DNNs) are known to make highly overconfident predi...
12/22/2020

Objective Evaluation of Deep Uncertainty Predictions for COVID-19 Detection

Deep neural networks (DNNs) have been widely applied for detecting COVID...
10/26/2020

Interpreting Uncertainty in Model Predictions For COVID-19 Diagnosis

COVID-19, due to its accelerated spread has brought in the need to use a...
04/28/2021

Reducing Risk and Uncertainty of Deep Neural Networks on Diagnosing COVID-19 Infection

Effective and reliable screening of patients via Computer-Aided Diagnosi...
06/13/2020

Uncertainty Estimation with Infinitesimal Jackknife, Its Distribution and Mean-Field Approximation

Uncertainty quantification is an important research area in machine lear...
05/12/2022

Training Uncertainty-Aware Classifiers with Conformalized Deep Learning

Deep neural networks are powerful tools to detect hidden patterns in dat...
04/09/2022

Uncertainty-Informed Deep Learning Models Enable High-Confidence Predictions for Digital Histopathology

A model's ability to express its own predictive uncertainty is an essent...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.