Feature Upsampling On Imagenet
Métriques
Average Drop
Average Increase
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Average Drop | Average Increase |
|---|---|---|
| deep-vit-features-as-dense-visual-descriptors | 11.48 | 4.97 |
| featup-a-model-agnostic-framework-for | 8.84 | 5.60 |
| featup-a-model-agnostic-framework-for | 9.83 | 5.24 |
| deep-image-prior | 10.57 | 5.16 |
| sapa-similarity-aware-point-affiliation-for | 10.62 | 4.85 |
| carafe-content-aware-reassembly-of-features | 10.24 | 4.96 |