Few Shot Class Incremental Learning On Cub
Métriques
Average Accuracy
Last Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Average Accuracy | Last Accuracy | Paper Title | Repository |
|---|---|---|---|---|
| PriViLege | 77.50 | 75.08 | Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners | |
| BOT | - | 63.75 | A Bag of Tricks for Few-Shot Class-Incremental Learning | - |
| PriViLege (ViT-L) | 79.20 | 76.43 | Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners | |
| SV-T | 78.65 | 76.17 | Semantic-visual Guided Transformer for Few-shot Class-incremental Learning | - |
| NC-FSCIL | 67.28 | 59.44 | Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning |
0 of 5 row(s) selected.