Image Classification on Flowers102 (Testing Accuracy)
42.75Testing AccuracyGrad-Mimic
Evaluation results
| Method | Links | |
|---|---|---|
| Grad-MimicNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 42.75 | |
| AGRANoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 41.81 | |
| Rho-LossNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 41.55 | |
| Grad-MimicNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 37.1 | |
| AGRANoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 36.28 | |
| Rho-LossNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 35.71 | |
| Grad-MimicNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 31.71 | |
| AGRANoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 31.49 | |
| Rho-LossNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 30.02 | |
| SGDNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 28.64 | |
| Grad-MatchNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 27 | |
| SGDNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 21.5 | |
| Grad-MatchNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 20.21 | |
| Grad-NormNoise Level=0.4, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 18.23 | |
| SGDNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 15.43 | |
| Grad-MatchNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 14.9 | |
| Grad-NormNoise Level=0.5, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 13.9 | |
| Grad-NormNoise Level=0.6, Evaluation Protocol=linear probing, Backbone=ViT-B/162025.01 | 10.49 |