search

sud0301 / essentials_for_CIL

Official repository of the paper 'Essentials for Class Incremental Learning'
40 stars 9 forks source link

About icarl_construct_exemplar_set function #3

Open superduduguan opened 3 years ago

superduduguan commented 3 years ago

Hi, I think the following codes seem not proper: https://github.com/sud0301/essentials_for_CIL/blob/c7eb378c822792977d96daa5dd98c0202263ec44/main_cifar.py#L321-L337 After debugging I find that when features[idx, :] = 0.0 implemented, exemplar_features is also set to 0, thus S is always full of 0 at any time, making it meaningless. I am not sure whether it is a common problem or it is triggered due to my incompatible version of packages. Besides, what if the random saving strategy get the same index? Is it right the purpose of setting the corresponding feature to 0, so that in the next phase the repetitive sample has a large distance and will be deleted? But still, what if class_mean itself is close to 0?

haoweiz23 commented 3 years ago

I am confused about the meaning of S and mu_p, why not compute the distance between features and mu directly? Does anyone have idea about that?