DeepAI AI Chat
Log In Sign Up

Mitigating Label Noise through Data Ambiguation

by   Julian Lienen, et al.
Universität München
Universität Paderborn

Label noise poses an important challenge in machine learning, especially in deep learning, in which large models with high expressive power dominate the field. Models of that kind are prone to memorizing incorrect labels, thereby harming generalization performance. Many methods have been proposed to address this problem, including robust loss functions and more complex label correction approaches. Robust loss functions are appealing due to their simplicity, but typically lack flexibility, while label correction usually adds substantial complexity to the training setup. In this paper, we suggest to address the shortcomings of both methodologies by "ambiguating" the target information, adding additional, complementary candidate labels in case the learner is not sufficiently convinced of the observed training label. More precisely, we leverage the framework of so-called superset learning to construct set-valued targets based on a confidence threshold, which deliver imprecise yet more reliable beliefs about the ground-truth, effectively helping the learner to suppress the memorization effect. In an extensive empirical evaluation, our method demonstrates favorable learning behavior on synthetic and real-world noise, confirming the effectiveness in detecting and correcting erroneous training labels.


page 1

page 2

page 3

page 4


Synergistic Network Learning and Label Correction for Noise-robust Image Classification

Large training datasets almost always contain examples with inaccurate o...

Partial Multi-label Learning with Label and Feature Collaboration

Partial multi-label learning (PML) models the scenario where each traini...

Generating the Ground Truth: Synthetic Data for Label Noise Research

Most real-world classification tasks suffer from label noise to some ext...

Label Noise: Correcting a Correction

Training neural network classifiers on datasets with label noise poses a...

Mitigating Label Bias via Decoupled Confident Learning

Growing concerns regarding algorithmic fairness have led to a surge in m...

Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation

Complementary-label Learning (CLL) is a form of weakly supervised learni...

ProSelfLC: Progressive Self Label Correction for Target Revising in Label Noise

In this work, we address robust deep learning under label noise (semi-su...