Transferability On Classification Benchmark
Metrics
Kendall's Tau
Results
Performance results of various models on this benchmark
Model Name | Kendall's Tau | Paper Title | Repository |
|---|---|---|---|
| SFDA | 0.502 | Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space | - |
| LEEP | 0.390 | LEEP: A New Measure to Evaluate Transferability of Learned Representations | - |
| NLEEP | 0.228 | Ranking Neural Checkpoints | - |
| logme | 0.482 | LogME: Practical Assessment of Pre-trained Models for Transfer Learning | - |
| ETran | 0.562 | ETran: Energy-Based Transferability Estimation | - |
| PACTran | 0.266 | PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks | - |
0 of 6 row(s) selected.