Classification On Mhist
評価指標
Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| SwAV (ResNet-50) | 77.99 | Benchmarking Self-Supervised Learning on Diverse Pathology Datasets | |
| MoCo-v2 (ResNet-50) | 88.03 | Improved transferability of self-supervised learning models through batch normalization finetuning | - |
| SwAV (ResNet-50) | 83.21 | Improved transferability of self-supervised learning models through batch normalization finetuning | - |
| Supervised (ViT-S/16) | 81.68 | Benchmarking Self-Supervised Learning on Diverse Pathology Datasets | |
| MoCo-v2 (ResNet-50) | 85.88 | Benchmarking Self-Supervised Learning on Diverse Pathology Datasets | |
| Barlow Rwins (ResNet-50) | 81.27 | Benchmarking Self-Supervised Learning on Diverse Pathology Datasets | |
| Supervised (ResNet-50) | 78.92 | Benchmarking Self-Supervised Learning on Diverse Pathology Datasets | |
| DINO (ViT-S/16) | 79.43 | Benchmarking Self-Supervised Learning on Diverse Pathology Datasets | |
| Barlow Twins (ResNet-50) | 84.03 | Improved transferability of self-supervised learning models through batch normalization finetuning | - |
0 of 9 row(s) selected.