Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Rethinking deep active learning: Using unlabeled data at model training

Abstract : 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 active learning, while the study of latter in the context of deep learning is scarce and recent findings are not conclusive with respect to its benefit. Our idea is orthogonal to acquisition strategies by using more data, much like ensemble methods use more models. By systematically evaluating on a number of popular acquisition strategies and datasets, we find that the use of unlabeled data during model training brings a surprising accuracy improvement in image classification, compared to the differences between acquisition strategies. We thus explore smaller label budgets, even one label per class.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03047667
Contributor : Yannis Avrithis Connect in order to contact the contributor
Submitted on : Tuesday, December 8, 2020 - 9:56:36 PM
Last modification on : Wednesday, November 3, 2021 - 8:15:51 AM
Long-term archiving on: : Tuesday, March 9, 2021 - 8:16:36 PM

File

R023.1911.08177.active.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03047667, version 1
  • ARXIV : 1911.08177

Citation

Oriane Siméoni, Mateusz Budnik, Yannis Avrithis, Guillaume Gravier. Rethinking deep active learning: Using unlabeled data at model training. 2019. ⟨hal-03047667⟩

Share

Metrics

Record views

27

Files downloads

44