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
    13 Citations
    Adversarial Representation Active Learning
    • 6
    • PDF
    On Initial Pools for Deep Active Learning
    • PDF
    Deep Active Learning with Augmentation-based Consistency Estimation
    • Highly Influenced
    • PDF
    A Survey of Deep Active Learning
    • 1
    • PDF
    From Model-driven to Data-driven: A Survey on Active Deep Learning
    • PDF
    Diverse Complexity Measures for Dataset Curation in Self-driving
    • PDF
    Deep Neural-Gas Clustering for Instance Segmentation across Imaging Experiments
    • PDF
    A Semisupervised Learning Scheme with Self-Paced Learning for Classifying Breast Cancer Histopathological Images

    References

    SHOWING 1-10 OF 43 REFERENCES
    ASCENT: Active Supervision for Semi-Supervised Learning
    • 5
    Label Propagation for Deep Semi-Supervised Learning
    • 136
    • PDF
    Temporal Ensembling for Semi-Supervised Learning
    • 611
    • PDF
    Deep Bayesian Active Learning with Image Data
    • 500
    • Highly Influential
    • PDF
    Active Learning for Convolutional Neural Networks: A Core-Set Approach
    • 338
    • Highly Influential
    • PDF
    Cost-Effective Active Learning for Deep Image Classification
    • 266
    • Highly Influential
    • PDF
    Semi-Supervised Learning with Scarce Annotations
    • 14
    • PDF
    The Power of Ensembles for Active Learning in Image Classification
    • 159
    • Highly Influential
    • PDF
    Adversarial Active Learning for Deep Networks: a Margin Based Approach
    • 70
    • PDF
    Variational Adversarial Active Learning
    • 82
    • PDF