Continual Learning On Split Cifar 100
Metriken
Average Accuracy
BWT
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | |||
|---|---|---|---|
| CODE-CL | 77.21 | -1.1 | CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning |
| OFSCIL | 68.62 | - | 12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning |
0 of 2 row(s) selected.