MaxMatch : Semi-Supervised Learning With Worst-Case Consistency
In recent years, great progress has been made to incorporate unlabeled data to overcome the inefficiently supervised problem via semi-supervised learning (SSL). Most state-of-the-art models are based on the idea of pursuing consistent model predictions over unlabeled data toward the input noise, whi...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 5 vom: 21. Mai, Seite 5970-5987
|
|---|
| 1. Verfasser: |
Jiang, Yangbangyan
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Li, Xiaodan,
Chen, Yuefeng,
He, Yuan,
Xu, Qianqian,
Yang, Zhiyong,
Cao, Xiaochun,
Huang, Qingming |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|