Semi-Supervised Learning with Scarce Annotations

@article{Rebuffi2020SemiSupervisedLW,
  title={Semi-Supervised Learning with Scarce Annotations},
  author={Sylvestre-Alvise Rebuffi and S. Ehrhardt and K. Han and A. Vedaldi and Andrew Zisserman},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2020},
  pages={3294-3302}
}
  • Sylvestre-Alvise Rebuffi, S. Ehrhardt, +2 authors Andrew Zisserman
  • Published 2020
  • Computer Science, Mathematics
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • While semi-supervised learning (SSL) algorithms provide an efficient way to make use of both labelled and unlabelled data, they generally struggle when the number of annotated samples is very small. [...] Key Method The first is a simple but effective one: we leverage the power of transfer learning among different tasks and self-supervision to initialize a good representation of the data without making use of any label.Expand Abstract
    Rethinking deep active learning: Using unlabeled data at model training
    6
    Self-Supervised Contextual Bandits in Computer Vision
    Data Transformation Insights in Self-supervision with Clustering Tasks
    1
    Learning to Discover Novel Visual Categories via Deep Transfer Clustering
    13
    LSD-C: Linearly Separable Deep Clusters

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES
    When Semi-Supervised Learning Meets Transfer Learning: Training Strategies, Models and Datasets
    7
    Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
    246
    FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
    67
    Semi-supervised Deep Learning with Memory
    24
    Tri-net for Semi-Supervised Deep Learning
    25
    Smooth Neighbors on Teacher Graphs for Semi-Supervised Learning
    97
    Combining labeled and unlabeled data with co-training
    4595
    MixMatch: A Holistic Approach to Semi-Supervised Learning
    271
    Certainty-Driven Consistency Loss for Semi-supervised Learning
    8