About results in table1

[ideal-123]

Hi, thanks for you sharing codes. Here I have a question about which model exactly you used when test in cross-domain few-shot dataset in table 1. For example, you use the one tested best in mini-test or you have another evaluation to choose the model which can generalize best in all this datasets? Looking forward to your response, thanks.

[Haoqing-Wang]

Thanks for you focus on our work. We use the validation split of source domain dataset (e.g., miniImageNet) to choose the best model and hyper-parameters.