You could also train an autoencoder on the training set and then autoencode the input image and measure the residual part.
Yep, but:
given only model weights
Also, the cossim-based approach should work on arbitrary submodules of a given model! Also it’s fast!
You could also train an autoencoder on the training set and then autoencode the input image and measure the residual part.
Yep, but:
Also, the cossim-based approach should work on arbitrary submodules of a given model! Also it’s fast!