Bayesian losses for homoscedastic aleatoric uncertainty modeling in pollen image detection

The paper investigates the homoscedastic aleatoric uncertainty modeling for the detection of pollen in images. The new uncertainty modeling loss functions are presented, which are based on the focal and smooth L1 losses. The focal and smooth L1 losses proved their efficiency for the problem of imag...

詳細記述

書誌詳細

出版年:	Научно-технический вестник информационных технологий, механики и оптики
第一著者:	Natalia E. Khanzhina
フォーマット:	論文
言語:	英語
出版事項:	ITMO University 2021-08-01
主題:	bayesian deep learning bayesian inference aleatoric uncertainty pollen recognition object detection uncertainty quantification bayesian modeling
オンライン･アクセス:	https://ntv.ifmo.ru/file/article/20579.pdf