Image Classification On Red Miniimagenet 20
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Accuracy | Paper Title | Repository |
|---|---|---|---|
| FaMUS | 51.42 | Faster Meta Update Strategy for Noise-Robust Deep Learning | |
| NCR (ResNet-18) | 69.0 | Learning with Neighbor Consistency for Noisy Labels | |
| InstanceGM | 58.38 | Instance-Dependent Noisy Label Learning via Graphical Modelling | |
| InstanceGM-SS | 60.89 | Instance-Dependent Noisy Label Learning via Graphical Modelling | |
| PropMix | 61.24 | PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels |
0 of 5 row(s) selected.