Closed avijit9 closed 2 years ago
Hi
Yes, we have reported the values from the SAVA paper, but we got similar values when we ran the corresponding experiments at our end.
For source-only: use --lambda_bgm 0.0 --lambda_tpl 0.0
For target-supervised: run source-only as mentioned above, and keep --src_dataset
and --tgt_dataset
the same.
Thanks
Hi,
I would like to know if you have a script to run
source only
andtarget supervised
models? From the paper, I see that the values are exactly the same as SAVA, ECCV'20 paper. So, I would like to clarify if you report these values from the SAVA paper or do you have script to reproduce the results?TIA.