• Computer Science
  • Published in ICLR 2017

Training deep neural-networks using a noise adaptation layer

@inproceedings{Goldberger2017TrainingDN,
  title={Training deep neural-networks using a noise adaptation layer},
  author={Jacob Goldberger and Ehud Ben-Reuven},
  booktitle={ICLR},
  year={2017}
}
The availability of large datsets has enabled neural networks to achieve impressive recognition results. However, the presence of inaccurate class labels is known to deteriorate the performance of even the best classifiers in a broad range of classification problems. Noisy labels also tend to be more harmful than noisy attributes. When the observed label is noisy, we can view the correct label as a latent random variable and model the noise processes by a communication channel with unknown… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 85 CITATIONS

Deep learning with noisy supervision

Jiangchao Yao
  • 2019
VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Safeguarded Dynamic Label Regression for Generalized Noisy Supervision

VIEW 16 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

Cyclic Annealing Training Convolutional Neural Networks for Image Classification with Noisy Labels

  • 2018 25th IEEE International Conference on Image Processing (ICIP)
  • 2018
VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

What happens when self-supervision meets Noisy Labels?

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Masking: A New Perspective of Noisy Supervision

  • NeurIPS
  • 2018
VIEW 11 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Training a neural network based on unreliable human annotation of medical images

  • 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
  • 2018
VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS

Learning with Noisy Labels for Sentence-level Sentiment Classification

Hao Wang, Bing Liu, Chaozhuo Li, Yan Yang, Tianrui Li
  • IJCNLP 2019
  • 2019
VIEW 9 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 17 Highly Influenced Citations

  • Averaged 28 Citations per year from 2017 through 2019

  • 55% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 21 REFERENCES

Broad patterns of gene expression revealed by clustering analysis of tumor and normal colon tissues probed by oligonucleotide arrays.

  • Proceedings of the National Academy of Sciences of the United States of America
  • 1998
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Design of robust neural network classifiers

  • Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)
  • 1998
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Training deep neural-networks based on unreliable labels

  • 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2016
VIEW 2 EXCERPTS

Classification in the Presence of Label Noise: A Survey

  • IEEE Transactions on Neural Networks and Learning Systems
  • 2014
VIEW 2 EXCERPTS