IS-CAM formula error? about torch-cam HOT 4 CLOSED

Hi @noobgrow 👋

Thanks for reporting this! So actually, the author reached out to me before the paper even came out to experiment with it. He validated the implementation back then, so I didn't question whether there would be some difference with the upcoming paper 😅

So let me check the difference you're talking about and get back to you 🙂

Cheers ✌️

from torch-cam.

OK! thanks for your fantastic work! Waiting for you @frgfm ^.^

from torch-cam.

So, this is going to be annoying without LaTex for math rendering, but let's try 😅
In the paper:

alpha_k^c = 1 / N * sum\limits_{i=0}^N (C(M_i))
# Let's expand M_i
alpha_k^c = 1 / N * sum\limits_{i=0}^N (C(sum\limits_{j=0}^{i-1} j / N * X_0 * A_l^k))
# Now we can simplify the sum
alpha_k^c = 1 / N * sum\limits_{i=0}^N (C(\frac{i * (i - 1)}{2N} * X_0 * A_l^k))

In the code, X_0 * A_l^k is stored as scored_inputs (cf. https://github.com/frgfm/torch-cam/blob/master/torchcam/methods/activation.py#L411-L414)
and \frac{i * (i - 1)}{2N} is stored as _coeff (cf. https://github.com/frgfm/torch-cam/blob/master/torchcam/methods/activation.py#L430)

So this line https://github.com/frgfm/torch-cam/blob/master/torchcam/methods/activation.py#L437 computes C(M_i) from the paper, they are summed in the following lines, and finally I divide by N here https://github.com/frgfm/torch-cam/blob/master/torchcam/methods/activation.py#L445

However, I realize that the docstring has some errors, I'll correct it to fix the documentation 👍
Let me know if some things are still unclear!

from torch-cam.

Closing this as the docstring has been fixed and the rest of the explanations have been detailed! Feel free to reopen @noobgrow if that's not the case :)

from torch-cam.