mlsanityData to 7 Oct 2026

On Robust Learning from Noisy Labels: A Permutation Layer Approach

arXiv 2211.15890 ↗First posted 29 Nov 2022cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The existence of label noise imposes significant challenges (e.g., poor generalization) on the training process of deep neural networks (DNN). As a remedy, this paper introduces a permutation layer learning approach termed PermLL to dynamically calibrate the training process of the DNN subject to instance-dependent and instance-independent label noise. The proposed method augments the architecture of a conventional DNN by an instance-dependent permutation layer. This layer is essentially a convex combination of permutation matrices that is dynamically calibrated for each sample. The primary objective of the permutation layer is to correct the loss of noisy samples mitigating the effect of label noise. We provide two variants of PermLL in this paper: one applies the permutation layer to the model's prediction, while the other applies it directly to the given noisy label. In addition, we provide a theoretical comparison between the two variants and show that previous methods can be seen as one of the variants. Finally, we validate PermLL experimentally and show that it achieves state-of-the-art performance on both real and synthetic datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 41 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

31 of 41 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  7. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  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. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  11. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  12. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
19 more
  1. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  2. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  3. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  4. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  5. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  6. 2017Decoupling "when to update" from "how to update"cited by 230
  7. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  8. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  9. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  10. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  11. 2018Learning to Learn from Noisy Labeled Datacited by 160
  12. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  13. 2015Webly Supervised Learning of Convolutional Networkscited by 95
  14. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  15. 2013Classification with Asymmetric Label Noise: Consistency and Maximal Denoisingcited by 67
  16. 2020What Do Neural Networks Learn When Trained With Random Labels?cited by 58
  17. 2021Joint Negative and Positive Learning for Noisy Labelscited by 34
  18. 2022SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labelscited by 24
  19. 2020Robust Learning by Self-Transition for Handling Noisy Labelscited by 18

Built on by

Not cited yet.