Semi Supervised Image Classification On Cifar
평가 지표
Percentage error
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Percentage error |
|---|---|
| improved-techniques-for-training-gans | 15.59 |
| simmatch-semi-supervised-learning-with | 3.96 |
| self-meta-pseudo-labels-meta-pseudo-labels | 4.09 |
| 모델 4 | 4.13±0.11 |
| lidam-semi-supervised-learning-with-localized | 7.48 |
| meta-pseudo-labels | 3.89± 0.07 |
| laplacenet-a-hybrid-energy-neural-model-for | 4.99±0.08 |
| remixmatch-semi-supervised-learning-with-1 | 5.14 |
| enaet-self-trained-ensemble-autoencoding | 4.18 |
| doublematch-improving-semi-supervised | 4.65±0.17 |
| unsupervised-data-augmentation-1 | 5.27 |
| virtual-adversarial-training-a-regularization | 11.36 |
| triple-generative-adversarial-networks | 10.01 |
| global-local-regularization-via | 10.6 |
| flexmatch-boosting-semi-supervised-learning | 4.19±0.01 |
| in-defense-of-pseudo-labeling-an-uncertainty-1 | 4.86 |
| there-are-many-consistent-explanations-of | 5 |
| diff-sysc-an-approach-using-diffusion-models | 3.26±0.06 |
| dual-student-breaking-the-limits-of-the | 8.89 |
| dash-semi-supervised-learning-with-dynamic | 4.08±0.06 |
| triple-generative-adversarial-networks | 12.41 |
| fixmatch-simplifying-semi-supervised-learning | 4.31 |
| temporal-ensembling-for-semi-supervised | 12.16 |
| adaptive-boosting-for-domain-adaptation | 6.05±0.12 |
| interpolation-consistency-training-for-semi | 7.29 |
| contrastive-regularization-for-semi | 4.16 |
| interpolation-consistency-training-for-semi | 7.66 |
| shot-vae-semi-supervised-deep-generative | 6.11 |
| semi-supervised-learning-by-augmented | 8.72 |
| repetitive-reprediction-deep-decipher-for | 5.72 |
| semi-supervised-learning-with-ladder-networks | 20.4 |
| realmix-towards-realistic-semi-supervised | 6.38 |
| good-semi-supervised-learning-that-requires-a | 14.41 |
| in-defense-of-pseudo-labeling-an-uncertainty-1 | 6.39±0.02 |
| np-match-when-neural-processes-meet-semi | 4.11±0.02 |
| triple-generative-adversarial-networks | 6.54 |
| semi-supervised-learning-with-self-supervised | 11.65 |
| np-match-when-neural-processes-meet-semi | 4.25 |
| mean-teachers-are-better-role-models-weight | 6.28 |
| mixmatch-a-holistic-approach-to-semi | 6.24 |
| selfmatch-combining-contrastive-self | 4.06±0.08 |
| all-labels-are-not-created-equal-enhancing | 3.8±0.08 |
| dp-ssl-towards-robust-semi-supervised | 4.23±0.20 |
| laplacenet-a-hybrid-energy-neural-model-for | 4.35±0.10 |
| semi-supervised-semantic-segmentation-via | 5.79 |
| semi-supervised-learning-of-visual-features | 4.0 ± 0.25 |
| virtual-adversarial-training-a-regularization | 10.55 |