• Home
  • Search
  • A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise
  • Cite Icon6
  • https://doi.org/10.1609/aaai.v37i7.26004Copy DOI Icon

A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

As deep neural networks can easily overfit noisy labels, robust training in the presence of noisy labels is becoming an important challenge in modern deep learning. While existing methods address this problem in various directions, they still produce unpredictable sub-optimal results since they rely on the posterior information estimated by the feature extractor corrupted by noisy labels. Lipschitz regularization successfully alleviates this problem by training a robust feature extractor, but it requires longer training time and expensive computations. Motivated by this, we propose a simple yet effective method, called ALASCA, which efficiently provides a robust feature extractor under label noise. ALASCA integrates two key ingredients: (1) adaptive label smoothing based on our theoretical analysis that label smoothing implicitly induces Lipschitz regularization, and (2) auxiliary classifiers that enable practical application of intermediate Lipschitz regularization with negligible computations. We conduct wide-ranging experiments for ALASCA and combine our proposed method with previous noise-robust methods on several synthetic and real-world datasets. Experimental results show that our framework consistently improves the robustness of feature extractors and the performance of existing baselines with efficiency.

Similar Papers
  • Research Article
  • Citations358

Image classification with deep learning in the presence of noisy labels: A survey

  • Jan 13, 2021
  • Knowledge-Based Systems
  • Görkem Algan +1
  • Research Article
  • Citations2

Stochastic resetting mitigates latent gradient bias of SGD from label noise

  • Mar 12, 2025
  • Machine Learning: Science and Technology
  • Youngkyoung Bae +2
  • Research Article
  • Citations29

Robust Deep Neural Networks for Road Extraction From Remote Sensing Images

  • Sep 26, 2020
  • IEEE Transactions on Geoscience and Remote Sensing
  • Panle Li +14
  • Conference Article
  • Citations3

Matrix Smoothing: A Regularization For Dnn With Transition Matrix Under Noisy Labels

  • Jul 01, 2020
  • Xianbin Lv +2
  • Conference Article
  • Citations7

Sample-wise Label Confidence Incorporation for Learning with Noisy Labels

  • Oct 01, 2023
  • Chanho Ahn +4
  • Conference Article
  • Citations1000

Symmetric Cross Entropy for Robust Learning With Noisy Labels

  • Oct 01, 2019
  • Yisen Wang +5
  • Research Article
  • Citations2

Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise.

  • Jan 01, 2024
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
  • Bidur Khanal +3
  • Conference Article
  • Citations9

A Study on the Impact of Data Augmentation for Training Convolutional Neural Networks in the Presence of Noisy Labels

  • Oct 24, 2022
  • Emeson Pereira +2
  • Book Chapter
  • Citations2

Collaborative Learning with Pseudo Labels for Robust Classification in the Presence of Noisy Labels

  • Jan 01, 2020
  • Chanjong Park +6
  • Research Article
  • Citations1147

Learning From Noisy Labels With Deep Neural Networks: A Survey.

  • Nov 01, 2023
  • IEEE Transactions on Neural Networks and Learning Systems
  • Hwanjun Song +4
  • Research Article
  • Citations5

Knowledge Distillation Meets Label Noise Learning: Ambiguity-Guided Mutual Label Refinery.

  • Jan 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Runqing Jiang +5
  • Research Article
  • Citations22

Attentive-Adaptive Network for Hyperspectral Images Classification With Noisy Labels

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Leiquan Wang +5
  • Research Article
  • Citations1

Graph Neural Networks with Coarse- and Fine-Grained Division for mitigating label noise and sparsity.

  • Jul 01, 2025
  • Neural networks : the official journal of the International Neural Network Society
  • Shuangjie Li +5
  • Book Chapter
  • Citations2

Towards Robust Uncertainty Estimation in the Presence of Noisy Labels

  • Jan 01, 2022
  • Chao Pan +3
  • Research Article

GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise

  • Jun 24, 2025
  • Cloud Computing and Data Science
  • Moseli Mots'Oehli +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.