Semi Supervised Image Classification On Stl 1
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| remixmatch-semi-supervised-learning-with-1 | 93.82 |
| mixmatch-a-holistic-approach-to-semi | 89.82 |
| stacked-what-where-auto-encoders | 74.30 |
| comatch-semi-supervised-learning-with | 77.46 |
| diff-sysc-an-approach-using-diffusion-models | 99.36±0.20 |
| doublematch-improving-semi-supervised | 95.65±0.20 |
| enaet-self-trained-ensemble-autoencoding | 91.96 |
| fixmatch-simplifying-semi-supervised-learning | 94.83±0.63 |
| boosting-the-performance-of-semi-supervised | 95.22±0.29 |
| semi-supervised-learning-with-context | 77.80 |
| np-match-when-neural-processes-meet-semi | 94.53 |