search

floodsung / LearningToCompare_FSL

PyTorch code for CVPR 2018 paper: Learning to Compare: Relation Network for Few-Shot Learning (Few-Shot Learning part)
MIT License
1.04k stars 268 forks source link

some questions regarding the accuracies #3

Closed ghost closed 6 years ago

ghost commented 6 years ago

Hi, I read both old and new version of the paper and found that the "shallow" RN in new version of the paper has lower accuracy than the one in older version of the paper, despite the number of layers and number of filters in each layer are exactly the same, what makes the accuracy become lower?

Also, In the older version of the paper, it report the "deeper" RN with much better performance, and stated that the model can benefit from a deeper structure, but when I added only 2 additional conv layer on embedding part of the model and trained it on mini-imagenet, it was overfitted after about 80000 episode and get poor test accuracy which is below 0.60, Am I missing any trick to make it deeper?

floodsung commented 6 years ago

Hi， 1） We trained mini-imagenet with valid set in our old version. We found that most of the other methods trained without valid set so that we retrain it with only train net. Therefore, the accuracy becomes lower. 2) Due to the lack of valid set, we also faced overfitting problem when training deeper RN. Therefore, we get rid of this part in our new version.