OoDAnalyzer : Interactive Analysis of Out-of-Distribution Samples
One major cause of performance degradation in predictive models is that the test samples are not well covered by the training data. Such not well-represented samples are called OoD samples. In this article, we propose OoDAnalyzer, a visual analysis approach for interactively identifying OoD samples...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on visualization and computer graphics. - 1996. - 27(2021), 7 vom: 12. Juli, Seite 3335-3349
|
|---|
| 1. Verfasser: |
Chen, Changjian
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Yuan, Jun,
Lu, Yafeng,
Liu, Yang,
Su, Hang,
Yuan, Songtao,
Liu, Shixia |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2021
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on visualization and computer graphics
|
|---|
| Schlagworte: | Journal Article |
|---|