Training Deep Neural Networks on Noisy Labels with Bootstrapping

@article{Reed2014TrainingDN,
  title={Training Deep Neural Networks on Noisy Labels with Bootstrapping},
  author={Scott E. Reed and Honglak Lee and Dragomir Anguelov and Christian Szegedy and Dumitru Erhan and Andrew Rabinovich},
  journal={CoRR},
  year={2014},
  volume={abs/1412.6596}
}
Current state-of-the-art deep learning systems for visual object recognition and detection use purely supervised training with regularization such as dropout to avoid overfitting. The performance depends critically on the amount of labeled examples, and in current practice the labels are assumed to be unambiguous and accurate. However, this assumption often does not hold; e.g. in recognition, class labels may be missing; in detection, objects in the image may not be localized; and in general… CONTINUE READING
Highly Cited
This paper has 22 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 7 times over the past 90 days. VIEW TWEETS

5 Figures & Tables

Topics

Statistics

051015201620172018
Citations per Year

Citation Velocity: 7

Averaging 7 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.
Blog posts, news articles and tweet counts and IDs sourced by
Altmetric.com