Latent Class-Conditional Noise Model
Learning with noisy labels has become imperative in the Big Data era, which saves expensive human labors on accurate annotations. Previous noise-transition-based methods have achieved theoretically-grounded performance under the Class-Conditional Noise model (CCN). However, these approaches builds u...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 8 vom: 22. Aug., Seite 9964-9980
|
|---|
| 1. Verfasser: |
Yao, Jiangchao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Han, Bo,
Zhou, Zhihan,
Zhang, Ya,
Tsang, Ivor W |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|