Something for ‘update the best model’

[Tom-Dongfang]

Hello, thanks for the great work. I want to talk about the main evaluation indices of the 'best model', and I noticed that ‘F1-score with regard to the change category’ is used as the main evaluation indices in your article. Then I found 'mF1' which is the mean F1-score with regard to the change category and unchange category was used for updating for the bset model. So I want to talk about whe Therefore, I would like to ask which indicator mF1 or F1_1( F1-score with regard to the change category) is more suitable as the basis for the output of the bset model. Thanks again and look forward to your reply.

[wgcban]

@Tom-Dongfang your question make sense for me!

Note that, F1_11 can be 1.0 if network predicts 1.0 as the output for all pixels. Hence, we used mF1 to update the best_model so we know the best_model can accurately predict both change and no-change classes (not only the change-class).

However, you can use F_1 as the performance indicator to update the best model -- which is mostly align with our objective.

Thanks!

[Tom-Dongfang]

Thank you for your reply！