Deep classifier neural networks enter the terminal phase of training (TPT) when training
error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural …

Recently, over-parameterized deep networks, with increasingly more network parameters
than training samples, have dominated the performances of modern machine learning …

When training deep neural networks for classification tasks, an intriguing empirical
phenomenon has been widely observed in the last-layer classifiers and features, where (i) …

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 …

Following the success of GPT4, there has been a surge in interest in multimodal large
language model (MLLM) research. This line of research focuses on developing general …

A recent study has shown a phenomenon called neural collapse in that the within-class
means of features and the classifier weight vectors converge to the vertices of a simplex …

The modern strategy for training deep neural networks for classification tasks includes
optimizing the network's weights even after the training error vanishes to further push the …

While cross entropy (CE) is the most commonly used loss function to train deep neural
networks for classification tasks, many alternative losses have been developed to obtain …

Neural Collapse refers to the remarkable structural properties characterizing the geometry of
class embeddings and classifier weights, found by deep nets when trained beyond zero …

The recently discovered Neural Collapse (NC) phenomenon occurs pervasively in today's
deep net training paradigm of driving cross-entropy (CE) loss towards zero. During NC, last …