[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
Hi, thank you for the outstanding work!! I have a question on the relprop function of Conv2D.
Based on the formula for LRP in the paper corresponding to the repository you provided in Issue #26, the current implementation appears to be incorrect. This cannot guarantee conservativeness.
The current implementation is as follows:
Such an implementation is equivalent to:
A implementation that I believe is correct is as follows:
Looking forward to your reply!!
Hi, thank you for the outstanding work!! I have a question on the relprop function of Conv2D.
Based on the formula for LRP in the paper corresponding to the repository you provided in Issue #26, the current implementation appears to be incorrect. This cannot guarantee conservativeness.
The current implementation is as follows:
Such an implementation is equivalent to:
A implementation that I believe is correct is as follows:
Looking forward to your reply!!