Image Classification on STL10 (Testing Accuracy)
97.16Testing AccuracyGrad-Mimic
Evaluation results
| Method | Links | |
|---|---|---|
| Grad-MimicNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 97.16 | |
| Rho-LossNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 97.1 | |
| Grad-MimicNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 97 | |
| Grad-MimicNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 96.9 | |
| Rho-LossNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 96.83 | |
| Rho-LossNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 96.49 | |
| SGDNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 96.26 | |
| AGRANoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 96.19 | |
| Grad-MatchNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 96.06 | |
| SGDNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 95.49 | |
| Grad-MatchNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 95.34 | |
| AGRANoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 95.15 | |
| SGDNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 93.56 | |
| Grad-MatchNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 93.44 | |
| AGRANoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 93.11 | |
| Grad-NormNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 68.7 | |
| Grad-NormNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 59.55 | |
| Grad-NormNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 49.68 |