Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?. (arXiv:2203.09081v3 [cs.LG] UPDATED)

Modern deep neural networks for classification usually jointly learn a
backbone for representation and a linear classifier to output the logit of each
class. A recent study has shown a phenomenon called neural collapse that the
within-class means of features and the classifier vectors converge to the
vertices of a simplex equiangular tight frame (ETF) at the terminal phase of
training on a balanced dataset. Since the ETF geometric structure maximally
separates the pair-wise angles of all classes in the …

arxiv classifier deep neural network network neural collapse neural network