Incremental Learning On Cifar100B020Step
Métriques
Average Incremental Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Average Incremental Accuracy | Paper Title | Repository |
|---|---|---|---|
| DER(ResNet-18) | 73.98 | DER: Dynamically Expandable Representation for Class Incremental Learning | |
| FOSTER | 70.65 | FOSTER: Feature Boosting and Compression for Class-Incremental Learning | |
| TCIL | 75.11 | Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning | |
| TCIL-Lite | 75.47 | Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning |
0 of 4 row(s) selected.