Active Learning with Bayesian UNet for Efficient Semantic Image Segmentation

Active Learning with Bayesian UNet for Efficient Semantic Image Segmentation

We present a sample-efficient image segmentation method using active learning, we call it Active Bayesian UNet, or AB-UNet. This is a convolutional neural network using batch normalization and max-pool dropout. The Bayesian setup is achieved by exploiting the probabilistic extension of the dropout m...

Full description

Bibliographic Details
Main Authors: Isah Charles Saidu, Lehel Csató
Format: Article
Language:English
Published: MDPI AG 2021-02-01
Series:Journal of Imaging
Subjects:
Bayesian, active learning
Bayesian learning
convolutional networks
AB-UNet
stochastic gradient descent
Online Access:https://www.mdpi.com/2313-433X/7/2/37

Internet

https://www.mdpi.com/2313-433X/7/2/37

Similar Items