mlsanityData to 7 Oct 2026

Deep Learning with Label Noise: A Hierarchical Approach

arXiv 2205.14299 ↗First posted 28 May 2022cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are susceptible to label noise. Existing methods to improve robustness, such as meta-learning and regularization, usually require significant change to the network architecture or careful tuning of the optimization procedure. In this work, we propose a simple hierarchical approach that incorporates a label hierarchy when training the deep learning models. Our approach requires no change of the network architecture or the optimization procedure. We investigate our hierarchical network through a wide range of simulated and real datasets and various label noise types. Our hierarchical approach improves upon regular deep neural networks in learning with label noise. Combining our hierarchical approach with pre-trained models achieves state-of-the-art performance in real-world noisy datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 58 references that are in the map. First posted on arXiv 28 May 2022.

Builds on

38 of 58 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  5. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  6. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  7. 2017A Closer Look at Memorization in Deep Networkscited by 936
  8. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  9. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  10. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  11. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  12. 2015Weight Uncertainty in Neural Networkscited by 554
26 more
  1. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  2. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 441
  3. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  4. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  5. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  6. 2014One weird trick for parallelizing convolutional neural networkscited by 264
  7. 2017Decoupling "when to update" from "how to update"cited by 230
  8. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  9. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  10. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  11. 2017Learning from Noisy Labels with Distillationcited by 160
  12. 2019Image Classification with Deep Learning in the Presence of Noisy Labels: A Surveycited by 101
  13. 2017Learning with Biased Complementary Labelscited by 93
  14. 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 87
  15. 2014Making Risk Minimization Tolerant to Label Noisecited by 54
  16. 2019On Symmetric Losses for Learning from Corrupted Labelscited by 53
  17. 2017B-CNN: Branch Convolutional Neural Network for Hierarchical Classificationcited by 37
  18. 2017Learning Deep Networks from Noisy Labels with Dropout Regularizationcited by 32
  19. 2018A Semi-Supervised Two-Stage Approach to Learning from Noisy Labelscited by 29
  20. 2020Label Noise Types and Their Effects on Deep Learningcited by 29
  21. 2020Meta Soft Label Generation for Noisy Labelscited by 21
  22. 2020NoiseRank: Unsupervised Label Noise Reduction with Dependence Modelscited by 20
  23. 2015Auxiliary Image Regularization for Deep CNNs with Noisy Labelscited by 14
  24. 2021On the Robustness of Monte Carlo Dropout Trained with Noisy Labelscited by 11
  25. 2021Inducing a hierarchy for multi-class classification problemscited by 5
  26. 2020Robust Deep Learning with Active Noise Cancellation for Spatial Computingcited by 2

Built on by

Not cited yet.