BiaSwap: Removing dataset bias with bias-tailored swapping augmentation
Open paper
Benchmark
Model
Rank
Results
action-recognition-on-bar
BiaSwap
–
Accuracy: 52.44
facial-attribute-classification-on-bffhq
BiaSwap
–
Bias-Conflicting Accuracy: 58.87
Rank counts only results with a code link.