Results for VisDA-C dadaset

[Leesoon1984]

While Fine-tuning the distilled model, the performance on the VisDA-C dataset drops, the results are as follows:

seed=2019: 74.98 --> 74.80
seed=2020: 76.17 --> 75.17
seed=2021: 79.8 --> 78.6.

The learning rate setting for VisDA-C dataset may matter.

[tim-learn]

While Fine-tuning the distilled model, the performance on the VisDA-C dataset drops, the results are as follows:

seed=2019: 74.98 --> 74.80
seed=2020: 76.17 --> 75.17
seed=2021: 79.8 --> 78.6.

The learning rate setting for VisDA-C dataset may matter.

Sorry for the late reply, I will upload the code for VisDA-C in the following month.

[zou-yawen]

While Fine-tuning the distilled model, the performance on the VisDA-C dataset drops, the results are as follows:

seed=2019: 74.98 --> 74.80
seed=2020: 76.17 --> 75.17
seed=2021: 79.8 --> 78.6.

The learning rate setting for VisDA-C dataset may matter.

hello, I try to repeat the result for VisDA-C dataset with DINE, I can't get the result could you please tell me your parameters