Image Classification on Indoor 80% independent noise (test)
34.08Top-1 AccuracyREGSL
Evaluation Results
| Method | Links | |
|---|---|---|
| REGSLBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 34.08 | |
| ELRBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 31.24 | |
| APLBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 30.9 | |
| l2-PGMBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 30.15 | |
| SCEBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 29.85 | |
| SATBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 29.6 | |
| GCEBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 29.58 | |
| Fine-tuningBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 27.09 | |
| DACBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 26.69 | |
| LSBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 25.82 |