Probability Calibration on ImageNet 16H Noise Level 95
3.23ECEP+L
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| P+LBackbone=VGG-19, Calibration fitting data size=5000, Evaluator type=Recalibrated Combination2021.09 | 3.23 | 0.69 | 0.32 | |
| P+LBackbone=VGG-19, Calibration fitting data size=5000, Evaluator type=Combination2021.09 | 4.56 | 0.72 | 0.39 | |
| P+LBackbone=VGG-19, Calibration fitting data size=10, Evaluator type=Combination2021.09 | 4.93 | 0.73 | 0.41 | |
| P+LBackbone=VGG-19, Calibration fitting data size=0, Evaluator type=Combination2021.09 | 5.72 | 0.82 | 0.52 | |
| VGG-19Backbone=VGG-19, Calibration fitting data size=5000, Evaluator type=Model2021.09 | 7.26 | 1.12 | 0.54 | |
| VGG-19Backbone=VGG-19, Calibration fitting data size=10, Evaluator type=Model2021.09 | 7.49 | 1.13 | 0.55 | |
| VGG-19Backbone=VGG-19, Calibration fitting data size=0, Evaluator type=Model2021.09 | 8.96 | 1.18 | 0.7 |