mlsanityData to 14 Oct 2026

A robust approach for deep neural networks in presence of label noise: relabelling and filtering instances during training

arXiv 2109.03748 ↗First posted 8 Sep 2021cs.LG cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning has outperformed other machine learning algorithms in a variety of tasks, and as a result, it is widely used. However, like other machine learning algorithms, deep learning, and convolutional neural networks (CNNs) in particular, perform worse when the data sets present label noise. Therefore, it is important to develop algorithms that help the training of deep networks and their generalization to noise-free test sets. In this paper, we propose a robust training strategy against label noise, called RAFNI, that can be used with any CNN. This algorithm filters and relabels instances of the training set based on the predictions and their probabilities made by the backbone neural network during the training process. That way, this algorithm improves the generalization ability of the CNN on its own. RAFNI consists of three mechanisms: two mechanisms that filter instances and one mechanism that relabels instances. In addition, it does not suppose that the noise rate is known nor does it need to be estimated. We evaluated our algorithm using different data sets of several sizes and characteristics. We also compared it with state-of-the-art models using the CIFAR10 and CIFAR100 benchmarks under different types and rates of label noise and found that RAFNI achieves better results in most cases.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 31 references that are in the map. First posted on arXiv 8 Sep 2021.

Builds on

20 of 31 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  4. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  5. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  6. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
  7. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  8. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
  9. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  10. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  11. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  12. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
8 more
  1. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  2. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  3. 2018Collaborative Learning for Deep Neural Networkscited by 69
  4. 2019Robust Bi-Tempered Logistic Loss Based on Bregman Divergencescited by 61
  5. 2017Learning Deep Networks from Noisy Labels with Dropout Regularizationcited by 32
  6. 2020COVIDGR dataset and COVID-SDNet methodology for predicting COVID-19 based on Chest X-Ray imagescited by 32
  7. 2017Automatic Handgun Detection Alarm in Videos Using Deep Learningcited by 15
  8. 2018Towards Highly Accurate Coral Texture Images Classification Using Deep Convolutional Neural Networks and Data Augmentationcited by 11

Built on by

Not cited yet.