Active learning with MaskAL reduces annotation effort for training Mask R-CNN.
Pieter M. BlokGert KootstraHakim Elchaoui ElghorBoubacar DialloFrits K. van EvertEldert J. van HentenPublished in: CoRR (2021)
Keyphrases
- annotation effort
- active learning
- training data
- training examples
- cellular neural networks
- semi supervised
- supervised learning
- selective sampling
- learning strategies
- random sampling
- labeled data
- training set
- learning algorithm
- machine learning
- unlabeled data
- online learning
- training process
- sample selection
- neural network
- pairwise
- experimental design
- training samples
- information retrieval