In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence...
A recent study has shown a phenomenon called neural collapse in that the...
In this paper, we propose the Generalized Parametric Contrastive Learnin...
Deep neural networks perform poorly on heavily class-imbalanced datasets...
In this paper, we propose Parametric Contrastive Learning (PaCo) to tack...
Deep neural networks may perform poorly when training datasets are heavi...
Deep learning algorithms face great challenges with long-tailed data
dis...
Self-attention mechanism has been widely used for various tasks. It is
d...
Despite the recent success of deep learning models in numerous applicati...
Recently, a number of learning-based optimization methods that combine
d...
Convolutional neural networks (CNNs) have recently achieved great succes...
Improving information flow in deep networks helps to ease the training
d...