A question about comparing metrics in oxford robotcar

[Bryan-ZhengRui]

Hello author, thank you very much for the code of adafusion, here I have a question. I would like to ask if it is reasonable to make a direct comparison between the results obtained in the oxford robotcar in the paper, where you used 10 sequences of training and testing rules, while CORAL and MinkLoc++ used 45 sequences of training and testing rules.