Gradient Agreement Hinders the Memorization of Noisy Labels
The performance of deep neural networks (DNNs) critically relies on high-quality annotations, while training DNNs with noisy labels remains challenging owing to their incredible capacity to memorize the entire training set. In this work, we use two synchronously trained networks to reveal that noisy...
שמור ב:
| Principais autores: | , , , |
|---|---|
| פורמט: | Artigo |
| שפה: | Inglês |
| יצא לאור: |
MDPI AG
2023-01-01
|
| סדרה: | Applied Sciences |
| נושאים: | |
| גישה מקוונת: | https://www.mdpi.com/2076-3417/13/3/1823 |
| תגים: |
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
|
