Corpus ID: 210839228

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

@article{Sohn2020FixMatchSS,
  title={FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence},
  author={Kihyuk Sohn and David Berthelot and Chun-Liang Li and Zizhao Zhang and Nicholas Carlini and Ekin D. Cubuk and Alex Kurakin and Han Zhang and Colin Raffel},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.07685}
}
  • Kihyuk Sohn, David Berthelot, +6 authors Colin Raffel
  • Published in ArXiv 2020
  • Mathematics, Computer Science
  • Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization and pseudo-labeling. Our algorithm, FixMatch, first generates pseudo-labels using the model's predictions on weakly-augmented unlabeled images. For a given image, the pseudo-label is only retained if the model produces a high-confidence prediction. The model… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 54 REFERENCES

    Adam: A Method for Stochastic Optimization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Reading Digits in Natural Images with Unsupervised Feature Learning

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    ImageNet: A large-scale hierarchical image database

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    AutoAugment: Learning Augmentation Strategies From Data

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL