Do you use validation data for training when report results on test split

[yaoqi-zd]

suppose the augmented VOC dataset can be splited into train_aug(10582)+val(1449)+test(1456),
when you report results on test split in your paper, do you use train_aug + val for training or just use train_aug?
thx!

[jiwoon-ahn]

Hi @yaoqi-zd,
Some works (e.g. DeepLab) did use (train_aug + val) for training and this could get us slightly better results, but we decided not to.

[yaoqi-zd]

THX!