Guided Zoom : Zooming into Network Evidence to Refine Fine-Grained Model Decisions
In state-of-the-art deep single-label classification models, the top- k (k=2,3,4, ...) accuracy is usually significantly higher than the top-1 accuracy. This is more evident in fine-grained datasets, where differences between classes are quite subtle. Exploiting the information provided in the top k...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 11 vom: 25. Nov., Seite 4196-4202
|
|---|
| 1. Verfasser: |
Bargal, Sarah Adel
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Zunino, Andrea,
Petsiuk, Vitali,
Zhang, Jianming,
Saenko, Kate,
Murino, Vittorio,
Sclaroff, Stan |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2021
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|