-
Notifications
You must be signed in to change notification settings - Fork 322
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
GeM pooling parameter #47
Comments
The converged I don't have evolution of the |
Thanks! No problem if you don't have the curve, I am definitely more interested in the final value. I am training a ResNet50 with ArcFace loss, GeM pooling, whitening layer, but somehow the GeM power keeps converging to 1 (average pooling). I tried accelerating the LR (as done in your code), but it didn't really help. I guess it's hard to debug this, but if you have any thoughts on what might be wrong here please let me know :) |
I haven't tried training with ArcFace loss, but that should not be the problem. Maybe try the opposite, reduce the LR for |
I plot loss vs epoch for Triplet (margin=0,5), Contrastive (margin=0,5) and ArcFace (margin=0,5, scale=1.0) losses as follows.
I wonder if we can conclude/generalize that ArcFace loss outperforms both Contrastive and Triplet losses in CNNs incorporated with GeM pooling layers in global feature extraction? This statements is pointed out in paper: Unifying Deep Local and Global Features for Image Search:
|
Hi @filipradenovic ,
For your experiment on networks with whitening learned end-to-end, with triplet loss, trained on the Google Landmarks dataset 2018: could you share to which value the GeM pooling parameter
p
converged to?If you could share learning curve showing the evolution of
p
over the training run, that would be even better :)Thanks!
The text was updated successfully, but these errors were encountered: