CODEWITHSUNDEEP
image-segmentationsemantic-segmentationmedical-imaging
fatemeh_p
fatemeh_p

Reputation: 123

How to train a semantic segmentation model with multiple masks?

I am working on a project about semantic segmentation in medical concepts where each image has multiple masks and each mask shows a different disease in the human eye, now I don't exactly know how to train my model with multiple masks. Should I stack the masks first or i will lose the information about different diseases, and how should I feed this information to my model?

Upvotes: 1

Views: 815

Answers (1)

Shai
Shai

Reputation: 114926

Before you train your model, you need first to think how you want it to be used afterward. At test time, how many masks do you want the model to output per input image? If you want your system to output multiple masks, then you should train a network with multiple binary output "heads". Alternatively, if you want the model to output a single mask with a different label per disease, then you should train a model with a single classification head, but with multiple classes per pixel.

Upvotes: 0

Related Questions