bbdamodaran

Results 4 comments of bbdamodaran

DeepJDOT might require proper initialization of target model. If you initialize the weights of the target model with source model, almost in all cases DeepJDOT works pretty well.

@jiangfanhan , I did also observe that the accuracy of CCE is much higher than reported in the paper, if early stopping criterion is used with respect to (noisy) validation...

I was not able to extract the tar file downloaded from the MediaFire. It shows that "Unable to read the header". @superwhyun have you managed to extract the tar file...

@superwhyun thanks for the details