Potential Energy based Mixture Model for Noisy Label Learning

arXiv:2405.01186v1 Announce Type: new
Abstract: Training deep neural networks (DNNs) from noisy labels is an important and challenging task. However, most existing approaches focus on the corrupted labels and ignore the importance of inherent data structure. To bridge the gap between noisy labels and data, inspired by the concept of potential energy in physics, we propose a novel Potential Energy based Mixture Model (PEMM) for noise-labels learning. We innovate a distance-based classifier with the potential energy regularization on its class …

abstract arxiv bridge concept cs.ai cs.lg data energy focus gap however importance labels networks neural networks training type