jiwoon-ahn / psa

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018
MIT License
385 stars 62 forks source link

Do you use validation data for training when report results on test split #15

Closed yaoqi-zd closed 5 years ago

yaoqi-zd commented 5 years ago

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 commented 5 years ago

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 commented 5 years ago

THX!