Open set recognition through Monte Carlo dropout-based uncertainty Online publication date: Tue, 04-Jan-2022
by Xiaojie Yin; Qinghua Hu; Gerald Schaefer
International Journal of Bio-Inspired Computation (IJBIC), Vol. 18, No. 4, 2021
Abstract: Open set recognition has received much attention in recent years. In this paper, we present a novel open set recognition method that is able to obtain improved recognition by applying Monte Carlo dropout to capture uncertainty in order to yield high quality predicted probabilities. Experimental results on six benchmark datasets show that our method gives better open set recognition performance than other state-of-the-art methods, with at least 6.4%, 3.9%, 2.9% and 1.0% performance increase in AUROC on the challenging object datasets CIFAR-10, CIFAR+10, CIFAR+50 and TinyImageNet respectively. We also perform an analysis on the benefits of combining predictive uncertainty with an EVT-based open set recognition model which indicates that Monte Carlo dropout-based uncertainty allows to obtain high quality predicted probabilities and to learn more accurate open set recognition scores. This, in turn, helps to reduce the overlap between known and unknown classes, thus making them more separable.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Bio-Inspired Computation (IJBIC):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook