Questions about the attention visualization?

szc19990412 / TransMIL

TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification

363 stars 73 forks source link

Questions about the attention visualization? #14

Closed pzSuen closed 2 years ago

pzSuen commented 2 years ago

Hello,

Does it seem that you haven't mentioned how to compute the attention of tokens in the paper? And I also can't find the code to compute the heatmap and visualization.

Can you answer my questions? Looking forward to your replay.

szc19990412 commented 2 years ago

Hi. For the visualization part of Transformer, we visualized the attention values of class tokens in the self-attention matrix to the rest of the feature tokens. For the specific visualization code, we refer to the CLAM processing scheme. Hope it helps you.

Luan-zb commented 2 years ago

Hello，I have a question.In your paper, self attention is actually linear attention. Here, we show the product of attention score and value. How do you calculate the attention score? Can you answer my questions? Looking forward to your replay.

lihua8848 commented 11 months ago

Solution： https://github.com/gabemarx/BMI2002/issues/1