pith. sign in

arxiv: 1811.03821 · v3 · pith:MSINUROHnew · submitted 2018-11-09 · 💻 cs.LG · stat.ML

Skeptical Deep Learning with Distribution Correction

classification 💻 cs.LG stat.ML
keywords approachdeepdistributiontrainingclassificationcorrectiondatainput
0
0 comments X
read the original abstract

Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world applications. One solution is to make supervised learning robust with imperfectly labeled input. In this paper, we develop a distribution correction approach that allows deep neural networks to avoid overfitting imperfect training data. Specifically, we treat the noisy input as samples from an incorrect distribution, which will be automatically corrected during our training process. We test our approach on several classification datasets with elaborately generated noisy labels. The results show significantly higher prediction and recovery accuracy with our approach compared to alternative methods.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.