search

renmengye / inc-few-shot-attractor-public

Code for Paper "Incremental Few-Shot Learning with Attention Attractor Networks"
MIT License
118 stars 27 forks source link

Some questions about ResNet. #3

Open vaynelau opened 4 years ago

vaynelau commented 4 years ago

It is a really nice job! We tried to use resnet as a backbone just like what you did in our own experiment. However, it didn't improve performance as we expected and even performed worse than 4-conv. I wonder if there are some tricks when you trained your model with a resnet. Thank you very much.

renmengye commented 4 years ago

Hi, thank you for the interest in our work. I found that data augmentation and early stopping is important for training ResNet.