A Study on the Impact of Data Augmentation for Training Convolutional Neural Networks in the Presence of Noisy Labels-Reference-Cited by-同舟云学术

A Study on the Impact of Data Augmentation for Training Convolutional Neural Networks in the Presence of Noisy Labels

Published:2022-10-24 Issue: Volume: Page:
ISSN:
Container-title:2022 35th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)
language:
Short-container-title:

Author:

Pereira Emeson¹,Carneiro Gustavo²,Cordeiro Filipe R.³

Affiliation:

1. Universidade Federal Rural de Pernambuco,PPGIA,Department of Computing,Recife,Brazil

2. Australian Institute of Machine Learning University of Adelaide,School of Computer Science,Adelaide,Australia

3. Universidade Federal Rural de Pernambuco,Visual Computing Lab,Recife,Brazil

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9991741/9991742/09991791.pdf?arnumber=9991791

Reference28 articles.

1. Imae for noise-robust learning: Mean absolute error does not treat examples equally and gradient magnitude’s variance matters;wang;arXiv preprint arXiv 1903 12206,2019

2. Deep Residual Learning for Image Recognition

3. Photometric Transformer Networks and Label Adjustment for Breast Density Prediction

4. Co-teaching: Robust training of deep neural networks with extremely noisy labels;han;Advances in neural information processing systems,2018

5. AutoAugment: Learning Augmentation Strategies From Data

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Layer-by-layer reconstruction of fatigue damages in composites from thermal images by a Residual U-Net;Composites Science and Technology;2024-08

2. Pyramid Feature Attention Network for Speech Resampling Detection;Applied Sciences;2024-06-01

3. Aster: Encoding Data Augmentation Relations into Seed Test Suites for Robustness Assessment and Fuzzing of Data-Augmented Deep Learning Models;2023 IEEE 23rd International Conference on Software Quality, Reliability, and Security (QRS);2023-10-22