A U-Net based active learning method using MC Dropout uncertainty sampling reduces the number of annotations needed for myelin segmentation from 15 to 3 samples on small histology datasets.
Uncertainty in Deep Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep Active Learning for Axon-Myelin Segmentation on Histology Data
A U-Net based active learning method using MC Dropout uncertainty sampling reduces the number of annotations needed for myelin segmentation from 15 to 3 samples on small histology datasets.