Corpus ID: 12190952

Training deep neural-networks using a noise adaptation layer

@inproceedings{Goldberger2017TrainingDN,
  title={Training deep neural-networks using a noise adaptation layer},
  author={J. Goldberger and E. Ben-Reuven},
  booktitle={ICLR},
  year={2017}
}
  • J. Goldberger, E. Ben-Reuven
  • Published in ICLR 2017
  • Computer Science
  • The availability of large datsets has enabled neural networks to achieve impressive recognition results. [...] Key Method Thus we can apply the EM algorithm to find the parameters of both the network and the noise and to estimate the correct label. In this study we present a neural-network approach that optimizes the same likelihood function as optimized by the EM algorithm. The noise is explicitly modeled by an additional softmax layer that connects the correct labels to the noisy ones.Expand Abstract
    202 Citations
    Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
    • 45
    • PDF
    Learning to Learn From Noisy Labeled Data
    • 63
    • PDF
    Learning from Noisy Labels with Noise Modeling Network
    Learning from Noisy Labels with Deep Neural Networks: A Survey
    • 8
    • PDF
    Robust Inference via Generative Classifiers for Handling Noisy Labels
    • 24
    • PDF
    Error-Bounded Correction of Noisy Labels
    Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
    • 13
    • PDF
    Coresets for Robust Training of Neural Networks against Noisy Labels

    References

    SHOWING 1-10 OF 21 REFERENCES
    Training deep neural-networks based on unreliable labels
    • 46
    • PDF
    Learning from Noisy Labels with Deep Neural Networks
    • 157
    Training Deep Neural Networks on Noisy Labels with Bootstrapping
    • 425
    • Highly Influential
    • PDF
    Learning with Noisy Labels
    • 533
    • PDF
    Distilling the Knowledge in a Neural Network
    • 4,566
    • PDF
    Class Noise vs. Attribute Noise: A Quantitative Study
    • 544
    • PDF
    Learning Multiple Layers of Features from Tiny Images
    • 9,348
    • PDF
    Label-Noise Robust Logistic Regression and Its Applications
    • 99
    • PDF
    Adam: A Method for Stochastic Optimization
    • 52,670
    • PDF
    A comprehensive introduction to label noise
    • 54
    • PDF