New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
GCNet vs. Non-Local module #2
Comments
Both GCNet and non-local can be used to add global knowledge for distillation. And we compare them in ablation study. The lighter GCNet is easier to train for distillation. |
@yzd-v |
You may read the two papers carefully. In table 6, we just use global distillation without focal distillation. While the result in FKD is achieved with all losses. However, Faster RCNN can achieve 42.0 mAP with focal and global distillation together. |
@yzd-v |
@yzd-v
Hi, thanks for your simple and powerfull KD method. I have one question, why use GCNet rather commonly used Non-local module,
Have you test these two OPs since GCNet is little better than Non-local.(Maybe some experiments about these two modules can be added into your paper, since this is one question reviewers intuitively will ask)
The text was updated successfully, but these errors were encountered: