I have some confusion about the implementation of the algorithm about bilrp_explain_similarity HOT 2 OPEN

Thanks for your questions!

Re 1.) The projection head is mainly there to reduce the dimensionality of the embeddings, so if the dimensionality of your embedding allows computing all LRP maps individually, the random projection head can be skipped. We use random projections because they do not introduce additional parameters to be trained and have favorable theoretical properties (guarantees on the quality of the approximation, preservation of pairwise distances, and their robustness to noise).

Re 2.) The BiLRP explanations maps only require setting the gamma parameter, I would advise using the default values. The other parameters (the clip function, pool_sie, p-parameter, etc.) are only there for visualization of the pair-wise interactions. We describe their function in the supplement to our paper ( Appendix D ).

Re 3.) You can check the XAI-toolbox Zennit, there you can find a tutorial on LRP for ResNet-18 .

from bilrp_explain_similarity.

Thank you very much for the Q&A. I believe all my questions have been solved!

from bilrp_explain_similarity.