About masking ratio
RohollahHS opened this issue · comments
Seyed Rohollah Hosseyni commented
The masking ratio is randomly sampled from [0.7, 1]. Did you conduct an ablation study on the effect of different ranges for the masking ratio?
Thanks.
Tianhong Li commented
Similar to MAE we sweep the masking ratio and find 0.7 is the best. For different tasks/data, the optimal masking ratio is typically different.