Few Shot Image Classification On Omniglot 1 1
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy |
|---|---|
| tapnet-neural-network-augmented-with-task | 98.07% |
| matching-networks-for-one-shot-learning | 93.8% |
| hypertransformer-model-generation-for | 97.7 |
| how-to-train-your-maml | 97.65 |
| uncertainty-in-model-agnostic-meta-learning | 93.2 |
| prototypical-networks-for-few-shot-learning | 96% |
| decoder-choice-network-for-meta-learning | 99.11 |
| hyperbolic-image-embeddings | 95.9% |
| gradient-based-meta-learning-with-learned | 96.2% |
| meta-curvature | 88% |
| learning-to-remember-rare-events | 95% |
| few-shot-learning-with-global-class | 99.63 |
| adaptive-posterior-learning-few-shot-learning | 97.2% |
| rapid-adaptation-with-conditionally-shifted | 96.12% |
| meta-learning-without-memorization-1 | 83.3 |
| learning-to-compare-relation-network-for-few | 97.6% |
| on-first-order-meta-learning-algorithms | 89.43% |
| towards-a-neural-statistician | 93.2% |
| meta-learning-with-implicit-gradients | 96.18 |
| decoder-choice-network-for-meta-learning | 98.8% |