Binary classification from local and global feature selection

I want to train a deep leaning model, consisting of images. My question is which scenariowas chosen to train the model?

scenario 1 : I train images local context on Output 1, and I train images clobal contet on Output 2, Finally, combine these two outputs to get a binary classification.

scenario 2 : Train global and local context directly on the binary classification.

This is what I mean by local and global context (This is just an example):