Neural Collapse: A Review on Modelling Principles and Generalization. (arXiv:2206.04041v1 [cs.LG])

With a recent observation of the "Neural Collapse (NC)" phenomena by Papyan
et al., various efforts have been made to model it and analyse the
implications. Neural collapse describes that in deep classifier networks, the
class features of the final hidden layer associated with training data tend to
collapse to the respective class feature means. Thus, simplifying the behaviour
of the last layer classifier to that of a nearest-class center decision rule.
In this work, we analyse the principles which …

arxiv lg modelling neural collapse review