OREAL improves patch-based active learning for semantic segmentation by scoring superpixels with their maximum pixel uncertainty and using one-vs-rest entropy to balance classes.
Class-balanced active learn- ing for image classification, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation
OREAL improves patch-based active learning for semantic segmentation by scoring superpixels with their maximum pixel uncertainty and using one-vs-rest entropy to balance classes.