Corpus ID: 208158246

Rethinking deep active learning: Using unlabeled data at model training

@article{Simoni2019RethinkingDA,
  title={Rethinking deep active learning: Using unlabeled data at model training},
  author={Oriane Sim{\'e}oni and Mateusz Budnik and Yannis Avrithis and G. Gravier},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.08177}
}

Oriane Siméoni, Mateusz Budnik, +1 author G. Gravier

Published 2019

Computer Science

ArXiv

Active learning typically focuses on training a model on few labeled examples alone, while unlabeled ones are only used for acquisition. In this work we depart from this setting by using both labeled and unlabeled data during model training across active learning cycles. We do so by using unsupervised feature learning at the beginning of the active learning pipeline and semi-supervised learning at every active learning cycle, on all available data. The former has not been investigated before in… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed