loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Yulong Wang 1 ; 2 ; 3 ; Xiaohui Hu 1 ; 3 and Zhe Jia 2

Affiliations: 1 School of Computer Science (National Pilot Software Engineering School), Beijing University of Post and Telecommunications, Beijing, China ; 2 Science and Technology on Communication Networks Laboratory, Shijiazhuang, China ; 3 State Key Laboratory of Networking and Switching Technology, Beijing, China

Keyword(s): Noise Label, Noise Filtering, Weighted Correction, Deep Neural Network.

Abstract: To solve the problem of low model accuracy under noisy data sets, a filtered weighted correction training method is proposed. This method uses the idea of model fine-tuning to adjust and correct the trained deep neural network model using filtered data, which has high portability. In the data filtering process, the noise label filtering algorithm, which is based on the random threshold in the double interval, reduces the dependence on artificially set parameters, increases the reliability of the random threshold, and improves the filtering accuracy and the recall rate of clean samples. In the calibration process, to deal with sample imbalance, different types of samples are weighted to improve the effectiveness of the model. Experimental results show that the propose method can improve the F1 value of deep neural network model.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.209.66.87

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Wang, Y.; Hu, X. and Jia, Z. (2021). Filtered Weighted Correction Training Method for Data with Noise Label. In Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - DeLTA; ISBN 978-989-758-526-5; ISSN 2184-9277, SciTePress, pages 177-184. DOI: 10.5220/0010577901770184

@conference{delta21,
author={Yulong Wang. and Xiaohui Hu. and Zhe Jia.},
title={Filtered Weighted Correction Training Method for Data with Noise Label},
booktitle={Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - DeLTA},
year={2021},
pages={177-184},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010577901770184},
isbn={978-989-758-526-5},
issn={2184-9277},
}

TY - CONF

JO - Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - DeLTA
TI - Filtered Weighted Correction Training Method for Data with Noise Label
SN - 978-989-758-526-5
IS - 2184-9277
AU - Wang, Y.
AU - Hu, X.
AU - Jia, Z.
PY - 2021
SP - 177
EP - 184
DO - 10.5220/0010577901770184
PB - SciTePress