Question on dynamic results about ua-mt

[yulequan]

Hi Jun,

Thanks for your interest in our work. Actually, the results of each model are diverse due to the small number of data in the medical image domain. Most of the results in the paper are the average results of three runs.

Furthermore, we also find the UAMT-UN is more robust (stable) than UAMT. So I would suggest you to add the consistency loss on unlabeled data only and then to see if we can obtain further improvement by adding consistency loss on labeled data.

[JunMa11]

Hi @yulequan ,

Thanks for your reply very much.
It's interesting, I train the UAMT_unlabel model twice on the same GPU server. However, the test results are exactly the same.

1st training

2nd training

Are the results of each model only diverse on different GPU servers?

Best,
Jun

[yulequan]

I have fixed the random seed in the code. So if you run the experiment on the same machine, the results should be similar. I am not sure if we can get the same results on different machine and environments even with the same random seed.

[JunMa11]

Got it. Thanks for your reply very much.