Implementation of TADAM: Task dependent adaptive metric for improved few-shot learning

[diego91964]

Problem
What do you want to do? What is blocking you?

I am reading an article and would like to discuss the possibility of implementing it in the prototypical network (https://arxiv.org/abs/1805.10123).

It would require the creation of a block to represent TEN layer, however the implementation of resnet12 uses a library and would have to be replaced by its own implementation.

What do you think about the proposal in this article for improving the calculation of the loss function?

[ebennequin]

Hi Diego!

TADAM is not on my roadmap at the moment, but I agree it would be a nice addition to the library and I'd be happy to help you if you want to implement it!

We can design the specific TADAM ResNet architecture in easyfsl.modules, and an example notebook adapted to the specific episodic training process.