grypesc / SEED

ICLR2024 paper on Continual Learning

Home Page:https://arxiv.org/abs/2401.10191

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About the parameters in Table 3

BlacknoSheep opened this issue · comments

In Table 3, it is shown that SEED utilizes 3.2 million parameters, whereas ResNet18 has 11.7 million parameters. Could you clarify which part of the parameters is referred to by "#Params." in the table?

Hello, thanks for interest in this work.
As stated in Appendix A.1, we utilize ResNet32 for Tab.3 which has ~0.46M parameters. Then, you can calculate the number of total parameters (network weights and Gausses) using Eq. 3 in Appendix A.3. Hope that helps!

Hello, thanks for interest in this work. As stated in Appendix A.1, we utilize ResNet32 for Tab.3 which has ~0.46M parameters. Then, you can calculate the number of total parameters (network weights and Gausses) using Eq. 3 in Appendix A.3. Hope that helps!

Thanks!