Monte Carlo Concrete DropPath for epistemic uncertainty estimation in pollen images classification

The paper presents the results of a new method for training the NASNet neural network called Monte Carlo Concrete DropPath for epistemic uncertainty estimation to classify pollen images. The developed method is compared with existing methods for epistemic uncertainty estimation. The method turns an...

Full description

Bibliographic Details

Published in:	Научно-технический вестник информационных технологий, механики и оптики
Main Author:	Natalia E. Khanzhina
Format:	Article
Language:	English
Published:	ITMO University 2021-12-01
Subjects:	bayesian deep learning variational inference epistemic uncertainty pollen recognition image recognition uncertainty estimation
Online Access:	https://ntv.ifmo.ru/file/article/20900.pdf