Classification on ImageNet 16H noise level 110
11.62Error RateP+L (MAP TS)
Evaluation Results
| Method | Links | |
|---|---|---|
| P+L (MAP TS)Backbone=VGG-19, Number of seeds=25, Labeled data points=5067-5152, Calibration=MAP TS2021.09 | 11.62 | |
| P+L (IMax Binning)Backbone=VGG-19, Number of seeds=25, Labeled data points=5067-5152, Calibration=IMax Binning2021.09 | 12.3 | |
| P+L (Uncalibrated)Backbone=VGG-19, Number of seeds=25, Labeled data points=5067-51522021.09 | 12.59 | |
| P+L (Ensemble TS)Backbone=VGG-19, Number of seeds=25, Labeled data points=5067-5152, Calibration=Ensemble TS2021.09 | 13.18 | |
| L+LBackbone=VGG-19, Number of seeds=25, Labeled data points=5067-51522021.09 | 14.07 | |
| P+LBackbone=GoogLeNet, Calibration=MAP TS2021.09 | 14.09 | |
| P+LBackbone=GoogLeNet, Calibration=IMax Binning2021.09 | 14.53 | |
| P+LBackbone=GoogLeNet, Calibration=Ensemble TS2021.09 | 14.76 | |
| P+LBackbone=GoogLeNet, Calibration=Uncalibrated2021.09 | 14.78 | |
| L+LBackbone=GoogLeNet2021.09 | 15.43 | |
| VGG-19Backbone=VGG-192021.09 | 15.51 | |
| GoogLeNetBackbone=GoogLeNet2021.09 | 19.09 | |
| Human2021.09 | 22.99 | |
| Human2021.09 | 22.99 |