# Prototypical Network - Should I train my backbone or a separate embedder?

When I read the prototypical paper Prototypical Networks for Few-shot Learning, I understand in Eq. 1 that I should train $$f_\phi$$, which takes as input $$x_i$$, which is already an embedding of an image. So, I understand from the paper that I should not train my backbone further, but only a new network that takes as input a first set of embeddings.

But in every github repo I find that implements prototypical networks, they train the whole network (using the loss defined just after Eq.2).

Did I misunderstood something?

• You can use mathjax on this site, so I recommend that you edit your post to do that.
– nbro
Jun 29, 2022 at 22:25