Group-Teaching: Learning Robust CNNs From Extremely Noisy Labels
Deep convolutional neural networks have achieved tremendous success in a variety of applications across many disciplines. However, their superior performance relies on correctly annotated large-scale datasets. It is very expensive and time-consuming to get the annotated large-scale datasets, especia...
Main Authors: | Yunping Zheng, Yuming Chen, Mudar Sarem |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9001093/ |
Similar Items
-
Training Robust Deep Neural Networks on Noisy Labels Using Adaptive Sample Selection With Disagreement
by: Hiroshi Takeda, et al.
Published: (2021-01-01) -
DCBT-Net: Training Deep Convolutional Neural Networks With Extremely Noisy Labels
by: Bekhzod Olimov, et al.
Published: (2020-01-01) -
FGCM: Noisy Label Learning via Fine-Grained Confidence Modeling
by: Shaotian Yan, et al.
Published: (2022-11-01) -
A Framework Using Contrastive Learning for Classification with Noisy Labels
by: Madalina Ciortan, et al.
Published: (2021-06-01) -
Gradient Agreement Hinders the Memorization of Noisy Labels
by: Shaotian Yan, et al.
Published: (2023-01-01)