Semi Supervised Image Classification On Svhn 1
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy |
|---|---|
| virtual-adversarial-training-a-regularization | 91.59 |
| triple-generative-adversarial-networks | 96.52 |
| mixmatch-a-holistic-approach-to-semi | 96.22 |
| realmix-towards-realistic-semi-supervised | 96.47 |
| dual-student-breaking-the-limits-of-the | 95.76 |
| mean-teachers-are-better-role-models-weight | 93.55 |
| triple-generative-adversarial-networks | 95.81 |
| mutexmatch-semi-supervised-learning-with-1 | 97.47 |
| enaet-self-trained-ensemble-autoencoding | 96.79 |
| mixup-beyond-empirical-risk-minimization | 60.03 |
| boosting-the-performance-of-semi-supervised | 97.7±0.03 |
| shrinking-class-space-for-enhanced-certainty | 98.04 |
| semi-supervised-learning-with-self-supervised | 91.68 |
| doublematch-improving-semi-supervised | 97.63±0.35 |
| regularization-with-stochastic | 82.35 |