Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Anja Witte"'
Publikováno v:
Industrial Artificial Intelligence, Vol 2, Iss 1, Pp 1-20 (2024)
Abstract The amount of labelled data in industrial use cases is limited because the annotation process is time-consuming and costly. As in research, self-supervised pretraining such as MAE resulted in training segmentation models with fewer labels, t
Externí odkaz:
https://doaj.org/article/31276db40a1e4255ae268aa32982a857
