Back to Search
Start Over
CoDC: Accurate Learning with Noisy Labels via Disagreement and Consistency.
- Source :
-
Biomimetics (2313-7673) . Feb2024, Vol. 9 Issue 2, p92. 15p. - Publication Year :
- 2024
-
Abstract
- Inspired by the biological nervous system, deep neural networks (DNNs) are able to achieve remarkable performance in various tasks. However, they struggle to handle label noise, which can poison the memorization effects of DNNs. Co-teaching-based methods are popular in learning with noisy labels. These methods cross-train two DNNs based on the small-loss criterion and employ a strategy using either "disagreement" or "consistency" to obtain the divergence of the two networks. However, these methods are sample-inefficient for generalization in noisy scenarios. In this paper, we propose CoDC, a novel Co-teaching-basedmethod for accurate learning with label noise via both Disagreement and Consistency strategies. Specifically, CoDC maintains disagreement at the feature level and consistency at the prediction level using a balanced loss function. Additionally, a weighted cross-entropy loss is proposed based on information derived from the historical training process. Moreover, the valuable knowledge involved in "large-loss" samples is further developed and utilized by assigning pseudo-labels. Comprehensive experiments were conducted on both synthetic and real-world noise and under various noise types. CoDC achieved 72.81% accuracy on the Clothing1M dataset and 76.96% (Top1) accuracy on the WebVision1.0 dataset. These superior results demonstrate the effectiveness and robustness of learning with noisy labels. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ARTIFICIAL neural networks
*BIOLOGICAL systems
*NERVOUS system
*MEMORIZATION
Subjects
Details
- Language :
- English
- ISSN :
- 23137673
- Volume :
- 9
- Issue :
- 2
- Database :
- Academic Search Index
- Journal :
- Biomimetics (2313-7673)
- Publication Type :
- Academic Journal
- Accession number :
- 175647896
- Full Text :
- https://doi.org/10.3390/biomimetics9020092