Image Classification on Indoor 60% independent noise (test)
57.59Top-1 AccuracyREGSL
Evaluation Results
| Method | Links | |
|---|---|---|
| REGSLBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 57.59 | |
| ELRBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 55.22 | |
| SCEBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 55.07 | |
| GCEBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 54.1 | |
| SATBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 52.84 | |
| APLBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 52.51 | |
| l2-PGMBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 51.24 | |
| LSBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 48.56 | |
| DACBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 47.44 | |
| Fine-tuningBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 44.6 |