szc19990412 / TransMIL

TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification
325 stars 72 forks source link

ABMIL in comparison #7

Closed InfinityBox closed 2 years ago

InfinityBox commented 2 years ago

I'm just wondering how to apply ABMIL in WSI for the comparison in Table 1? I have read ABMIL's code, the input size of its model is: (1, bag_length, 1, width, height), due to the images of the dataset being very small, memory problems may not occur. But when using WSI, bag_length, width and height are very big, so how to apply this method to WSIs like the result in Table 1?

szc19990412 commented 2 years ago

There may be some misunderstanding of the references here. You can refer to the code here to implement ABMIL, which is an attention MIL based on features: https://github.com/mahmoodlab/PORPOISE/blob/master/models/model_attention_mil.py