Regularizing Deep Networks With Semantic Data Augmentation
Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translation or rotation, are low-level, data-independent and class-agnostic operations, leading to limited diversity for augmente...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 7 vom: 21. Juli, Seite 3733-3748
|
|---|
| 1. Verfasser: |
Wang, Yulin
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Huang, Gao,
Song, Shiji,
Pan, Xuran,
Xia, Yitong,
Wu, Cheng |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|