Corpus ID: 203902373

Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates

@article{Liu2019PeerLF,
  title={Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates},
  author={Yang Liu and Hong-Yi Guo},
  journal={ArXiv},
  year={2019},
  volume={abs/1910.03231}
}
  • Yang Liu, Hong-Yi Guo
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • Learning with noisy labels is a common problem in supervised learning. Existing approaches require practitioners to specify \emph{noise rates}, i.e., a set of parameters controlling the severity of label noises in the problem. The specifications are either assumed to be given or estimated using additional approaches. In this work, we introduce a technique to learn from noisy labels that does not require a priori specification of the noise rates. In particular, we introduce a new family of loss… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-5 OF 5 CITATIONS

    Class2Simi: A New Perspective on Learning with Label Noise

    VIEW 1 EXCERPT

    Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning

    VIEW 1 EXCERPT
    CITES METHODS

    Label-Noise Robust Domain Adaptation

    VIEW 1 EXCERPT
    CITES METHODS

    Parts-dependent Label Noise: Towards Instance-dependent Label Noise

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 50 REFERENCES

    Learning with Noisy Labels

    VIEW 20 EXCERPTS
    HIGHLY INFLUENTIAL

    Classification with Noisy Labels by Importance Reweighting

    • Tongliang Liu, Dacheng Tao
    • Mathematics, Computer Science, Medicine
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 2016
    VIEW 1 EXCERPT

    Noise Tolerance Under Risk Minimization

    Online Learning of Noisy Data

    VIEW 2 EXCERPTS

    Learning in the Presence of Corruption

    VIEW 2 EXCERPTS