Learning and predicting the unknown class using evidential deep learning.

ABSTRACT: In practical deep-learning applications, such as medical image analysis, autonomous driving, and traffic simulation, the uncertainty of a classification model's output is critical. Evidential deep learning (EDL) can output this uncertainty for the prediction; however, its accuracy depends on a user-defined threshold, and it cannot handle training data with unknown classes that are unexpectedly contaminated or deliberately mixed for better classification of unknown class. To address these limitations, I propose a classification method called modified-EDL that extends classical EDL such that it outputs a prediction, i.e. an input belongs to a collective unknown class along with a probability. Although other methods handle unknown classes by creating new unknown classes and attempting to lear

SUBMITTER: Nagahama A 

PROVIDER: S-EPMC10492799 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature