Semi Supervised Image Classification On Svhn
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy |
|---|---|
| triple-generative-adversarial-networks | 96.04 |
| unsupervised-data-augmentation-1 | 97.54 |
| doublematch-improving-semi-supervised | 97.90 ± 0.07 |
| interpolation-consistency-training-for-semi | 96.47 |
| interpolation-consistency-training-for-semi | 96.11 |
| semi-supervised-learning-with-self-supervised | 94.41 |
| mixmatch-a-holistic-approach-to-semi | 96.73 |
| improved-techniques-for-training-gans | 91.89 |
| meta-pseudo-labels | 98.01 ± 0.07 |
| triple-generative-adversarial-networks | 96.55 |
| mean-teachers-are-better-role-models-weight | 96.05 |
| fixmatch-simplifying-semi-supervised-learning | 97.64±0.19 |
| remixmatch-semi-supervised-learning-with-1 | 97.17 |
| virtual-adversarial-training-a-regularization | 94.58 |
| repetitive-reprediction-deep-decipher-for | 96.36 |
| flow-contrastive-estimation-of-energy-based | 96.13 |
| enaet-self-trained-ensemble-autoencoding | 97.58 |