KNN-enhanced Deep Learning Against Noisy Labels

• URL: http://arxiv.org/abs/2012.04224v1
• Date: Tue, 8 Dec 2020 05:21:29 GMT
• Title: KNN-enhanced Deep Learning Against Noisy Labels
• Authors: Shuyu Kong and You Li and Jia Wang and Amin Rezaei and Hai Zhou
• Abstract summary: Supervised learning on Deep Neural Networks (DNNs) is data hungry. In this work, we propose to apply deep KNN for label cleanup. We iteratively train the neural network and update labels to simultaneously proceed towards higher label recovery rate and better classification performance.
• Score: 4.765948508271371
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Supervised learning on Deep Neural Networks (DNNs) is data hungry. Optimizing performance of DNN in the presence of noisy labels has become of paramount importance since collecting a large dataset will usually bring in noisy labels. Inspired by the robustness of K-Nearest Neighbors (KNN) against data noise, in this work, we propose to apply deep KNN for label cleanup. Our approach leverages DNNs for feature extraction and KNN for ground-truth label inference. We iteratively train the neural network and update labels to simultaneously proceed towards higher label recovery rate and better classification performance. Experiment results show that under the same setting, our approach outperforms existing label correction methods and achieves better accuracy on multiple datasets, e.g.,76.78% on Clothing1M dataset.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.