Corpus ID: 211076003

Fine-grained Uncertainty Modeling in Neural Networks

@article{Soni2020FinegrainedUM,
  title={Fine-grained Uncertainty Modeling in Neural Networks},
  author={Rahul Soni and Naresh Shah and Jimmy D. Moore},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.04205}
}
  • Rahul Soni, Naresh Shah, Jimmy D. Moore
  • Published in ArXiv 2020
  • Mathematics, Computer Science
  • Existing uncertainty modeling approaches try to detect an out-of-distribution point from the in-distribution dataset. We extend this argument to detect finer-grained uncertainty that distinguishes between (a). certain points, (b). uncertain points but within the data distribution, and (c). out-of-distribution points. Our method corrects overconfident NN decisions, detects outlier points and learns to say ``I don't know'' when uncertain about a critical point between the top two predictions. In… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 33 REFERENCES

    Detecting Adversarial Samples from Artifacts

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Human-Centric Justification of Machine Learning Predictions

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Handbook of Image and Video Processing

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL

    Evidential Deep Learning to Quantify Classification Uncertainty

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    On Calibration of Modern Neural Networks

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Latent Dirichlet Allocation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

    VIEW 1 EXCERPT