Facial Attribute Classification On Bffhq
Metrics
Bias-Conflicting Accuracy
Results
Performance results of various models on this benchmark
Model Name | Bias-Conflicting Accuracy | Paper Title | Repository |
|---|---|---|---|
| DCWP | 60.35 | Training Debiased Subnetworks with Contrastive Weight Pruning | |
| DebiAN | 62.8 | Discover and Mitigate Unknown Biases with Debiasing Alternate Networks | |
| BiaSwap | 58.87 | BiaSwap: Removing dataset bias with bias-tailored swapping augmentation | - |
0 of 3 row(s) selected.