blessu
commented
1 year ago Thanks a lot for your interest.
The parameter gamma in the function map_param is used for the rebalancing weighting part - mainly for normalization. It is intuitively generated by estimating the "center" (mean or median). You can find the parameter estimation step at the end of dataset_prep.ipynb for Reuters and PubMed respectively.
Since CB-NTR has a different reweighting approach than rebalancing weighting, the function map_param is not used in the loss function. Most of the other (hyper-)parameters were the same as in the ECCV'20 paper.
Giovani-Merlin
Firstly thank you for the great paper and for providing the code, but to use it in other applications/datasets, I'm trying to understand better the mapping parameters. Checking the Reuters and the PubMed training code, I can see that we have the parameters for the first:
map_param=dict(alpha=0.1, beta=10.0, gamma=0.9) And for the second: map_param=dict(alpha=0.1, beta=10.0, gamma=0.05) Have you done hyper-parameter optimisation for choosing this gamma, or does it comes from an "exact" approach?
For CB-NTR, we don't have this parameter (so all the parameters are equal for both datasets); therefore, it seems a "safer" loss to use in other datasets. Can you explain the method of obtention of these loss parameters? Thank you