facebookresearch/msn

How to change MSN loss to PMSN loss? (from paper "The Hidden Uniform Cluster Prior in Self-Supervised Learning")

faris-k opened this issue · 1 comments

I couldn't find an official code release for this paper arxiv.org/abs/2210.07277, in which an extension is proposed to MSN to allow arbitrary feature priors.

It looks like the main difference is a change of a single term in the loss function. Is that correct? How would I implement the changes mentioned in the PMSN paper?

Previous MSN loss:

image

New loss: Prior Matching for Siamese Networks, PMSN:

image