Closed NareshGuru77 closed 2 months ago
I think your metric is correct. We retrained the model after the paper was published, so the performance may differ from what was reported. Based on my experience, few-shot performance can vary significantly.
Thank you for your quick response!. So I can use the current numbers I get as the new results ?
yeah, I think so. :) Enjoy with the code.
Thank you!
There are discrepancies in the results of few-shot results and in one zero shot result as shown below:
However, results for zero-shot cs-det, cs-seg and sun - rgbd seg match with only slight deviations.
Would it be possible that I am looking at the wrong metric or maybe there is some other issue? Would be glad if you could help me with this. Thank you!.