Semi Supervised Image Classification On Cifar 11
평가 지표
Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Triple-GAN-V2 (ResNet-26) | 91.59 | Triple Generative Adversarial Networks | - |
| SESEMI SSL (ConvNet) | 82.12 | Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning | - |
| Triple-GAN-V2 (CNN-13, no aug) | 81.81 | Triple Generative Adversarial Networks | - |
| ICT (CNN-13) | 84.52 | Interpolation Consistency Training for Semi-Supervised Learning | - |
| Triple-GAN-V2 (CNN-13) | 85.00 | Triple Generative Adversarial Networks | - |
| Dual Student (600) | 85.83 | Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning | - |
| UPS (CNN-13) | 91.82 | In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning | - |
| MixMatch | 92.25 | MixMatch: A Holistic Approach to Semi-Supervised Learning | - |
| LiDAM | 89.04 | LiDAM: Semi-Supervised Learning with Localized Domain Adaptation and Iterative Matching | - |
0 of 9 row(s) selected.