About val dataset and the result of two baselines about udat

[Jay-Ye]

Hi. I have two questions:

1. It seems that there is no val dataset in NAT, so do you directly use the model saved in the last epoch to test?
2. Since the train set of NAT does not have labels and the two baselines(SiamCAR & SiamBAN) are supervised methods, I wonder whether the results of two baselines used to compare with UDAT are only trained on GOT-10K and VID.

Hi, thank you for your question.
A1: Actually, we sequentially test the last 10 trained checkpoints and select the one with the best performance.
A2: The performance of the two baselines is generated with the models released by their authors, which are generally trained on several datasets, more details can be found in the corresponding papers. To avoid a great disparity in the number of training samples in the source domain and target domain, we thus only use the GOT-10K and VID as the source domain datasets.

[cjyiiiing]

Thanks for your reply.