Bayesian Deep Learning Detection of Anomalies and Failure: Application To Medical Images

Giuseppina Carannante, Nidhal C. Bouaynaya

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep learning models trained solely on in-distribution data may not generalize well to anomalous data and may exhibit high confidence in incorrect predictions, leading to significant consequences in safety-critical applications such as medical diagnosis or autonomous driving. It is important for these models to be able to handle anomalous or Out-of-Distribution (OOD) data which are prevalent in many real-world scenarios. In this work, we leverage the predictive variance, i.e., second-order moment of the predictive distribution, of Bayesian models to identify anomalous data points. We test our anomaly and misclassification mechanism on medical image datasets and compare the detection performance of several Bayesian frameworks under various distributional shifts, i.e., noisy conditions, adversarial attacks and OOD data.

Original languageEnglish (US)
Title of host publicationProceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023
EditorsDanilo Comminiello, Michele Scarpiniti
PublisherIEEE Computer Society
ISBN (Electronic)9798350324112
DOIs
StatePublished - 2023
Externally publishedYes
Event33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023 - Rome, Italy
Duration: Sep 17 2023Sep 20 2023

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume2023-September
ISSN (Print)2161-0363
ISSN (Electronic)2161-0371

Conference

Conference33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023
Country/TerritoryItaly
CityRome
Period9/17/239/20/23

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Signal Processing

Fingerprint

Dive into the research topics of 'Bayesian Deep Learning Detection of Anomalies and Failure: Application To Medical Images'. Together they form a unique fingerprint.

Cite this