Baselines compared ...

[TiankaiHang]

Hi, thanks for your nice work!

You have listed some results of other methods (such as CCT), have you just re-implement the method under your settings?

As we know, the splits of dataset differ in those semi-sup papers.

Thanks.

[X-Lai]

Yes, you are right. The splits of datasets differ in different works and they also don't release the data lists, which makes it hard to compare with other works. Therefore, to fairly compare with different state-of-the-art methods, we use their official codes with our data lists.
The data lists we use are released in here. Thanks for your comment.

[TiankaiHang]

OK, thanks!