TMLC-Net: Transferable Meta Label Correction for Noisy Label Learning

TL;DR

TMLC-Net introduces a transferable meta-learning framework that effectively corrects noisy labels across diverse datasets and models, significantly improving robustness and accuracy in noisy label scenarios.

Contribution

The paper proposes TMLC-Net, a novel meta-learning approach that generalizes label correction strategies for various datasets and architectures without extensive retraining.

Findings

Outperforms state-of-the-art methods in accuracy and robustness.

Demonstrates high transferability across datasets and noise conditions.

Effectively models label noise dynamics with novel components.

Abstract

The prevalence of noisy labels in real-world datasets poses a significant impediment to the effective deployment of deep learning models. While meta-learning strategies have emerged as a promising approach for addressing this challenge, existing methods often suffer from limited transferability and task-specific designs. This paper introduces TMLC-Net, a novel Transferable Meta-Learner for Correcting Noisy Labels, designed to overcome these limitations. TMLC-Net learns a general-purpose label correction strategy that can be readily applied across diverse datasets and model architectures without requiring extensive retraining or fine-tuning. Our approach integrates three core components: (1) Normalized Noise Perception, which captures and normalizes training dynamics to handle distribution shifts; (2) Time-Series Encoding, which models the temporal evolution of sample statistics using a recurrent neural network; and (3) Subclass Decoding, which predicts a corrected label distribution based on the learned representations. We conduct extensive experiments on benchmark datasets with various noise types and levels, demonstrating that TMLC-Net consistently outperforms state-of-the-art methods in terms of both accuracy and robustness to label noise. Furthermore, we analyze the transferability of TMLC-Net, showcasing its adaptability to new datasets and noise conditions, and establishing its potential as a broadly applicable solution for robust deep learning in noisy environments.