Potential Energy based Mixture Model for Noisy Label Learning

TL;DR

This paper introduces a novel Potential Energy based Mixture Model (PEMM) that enhances noisy label learning in deep neural networks by leveraging data structure and potential energy concepts, achieving state-of-the-art results.

Contribution

The paper proposes a new potential energy regularization technique for class centers in a distance-based classifier, improving robustness to noisy labels in deep learning.

Findings

Achieves state-of-the-art performance on real-world datasets.

Enhances feature representations by preserving intrinsic data structures.

Improves noisy label tolerance in deep neural networks.

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 centers. Embedding our proposed classifier with existing deep learning backbones, we can have robust networks with better feature representations. They can preserve intrinsic structures from the data, resulting in a superior noisy tolerance. We conducted extensive experiments to analyze the efficiency of our proposed model on several real-world datasets. Quantitative results show that it can achieve state-of-the-art performance.