Batch-Spectral-Penalization

Batch-Spectral-Penalization copied to clipboard

LOW ACCURACY

3

I carried out your experiment as you described, but almost all the experimental results are 1% lower than reported in your paper, so I want to know more specific experimental...

buerzlh

Accuracy reported on the validation set of visda-2017 instead of test set atleast in the code. Are the results reported in BSP paper also on the validation set using the same code output?

1

The paper reports SOTA results compared to CDAN on VisDA-2017 dataset. However there might be some issues with the reproducibility. On a close look, the provided code only reports the...

sobalgi

Hi, Thanks for your great work and source code. I have a question about your code. In the train.py file, it seems that when noe >= 2, the model will...

zhunzhong07