xiaoeyuztj

No more update？

4

No more ICLR or CVPR2020 papers ? Maybe we could also contribute to the list?

About the calculation of the variance of R(output)

1

In the paper, there seems like the R is a random variable. So the variance of Z shouldn't be calculate by (1-lambda)**2, the way calculated in the code(IBA-paper-code/attribution_bottleneck/bottleneck/per_sample_bottleneck.py). This way...

The definition of some function seems missing...

5

https://github.com/Adamdad/Repfusion/blob/2fe77c4c3c75592b4ea308488a926cc408e1a116/classification_distill/mmcls/models/classifiers/repfusion.py#L15C54-L15C68 So where is the definition of the Repfusion_Base? In utils.py, there is no declaration named the base class...