Some question about use SSL to other domain adaptation framework

[YanLiang0813]

Hi, I attempt to use your SSL strategy to my own DA framework, but my performance seriously decreased (from the initial 44.3% to 41.5%).

My DA framework is similar to AdasegNet, and I use your SSL.py to generate the pseudo labels. My loss is : L = L_sourceseg + \lamdaL_da (1) L = L_sourceseg + \lamda1L_da +\lamda2*L_ssl (2) First, I use (1) to train my network, and the best mIoU is 44.3%. Then, I use the best model to generate pseudo labels (use SSL.py). Finally, I use the pseudo labels to train the Eq(2). But the result is decreased.

Could you give me some suggestion on how to use the pseudo labels?

[liyunsheng13]

I think I just use the pseudo labels as you described. But as you use a different DA framework, it's very hard for me to help you.