mlsanityData to 7 Oct 2026

SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels

arXiv 2211.11753 ↗First posted 20 Nov 2022cs.LG cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Annotating the dataset with high-quality labels is crucial for performance of deep network, but in real world scenarios, the labels are often contaminated by noise. To address this, some methods were proposed to automatically split clean and noisy labels, and learn a semi-supervised learner in a Learning with Noisy Labels (LNL) framework. However, they leverage a handcrafted module for clean-noisy label splitting, which induces a confirmation bias in the semi-supervised learning phase and limits the performance. In this paper, we for the first time present a learnable module for clean-noisy label splitting, dubbed SplitNet, and a novel LNL framework which complementarily trains the SplitNet and main network for the LNL task. We propose to use a dynamic threshold based on a split confidence by SplitNet to better optimize semi-supervised learner. To enhance SplitNet training, we also present a risk hedging method. Our proposed method performs at a state-of-the-art level especially in high noise ratio settings on various LNL benchmarks.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 53 of its 70 references that are in the map. First posted on arXiv 20 Nov 2022.

Builds on

53 of 70 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  7. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  8. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  9. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  10. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  11. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  12. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
38 more
  1. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  2. 2017A Closer Look at Memorization in Deep Networkscited by 936
  3. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  4. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  5. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  6. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  7. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  8. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  9. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  10. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  11. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  12. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  13. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  14. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  15. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
  16. 2021A Survey on Deep Semi-supervised Learningcited by 250
  17. 2015Semi-Supervised Learning with Ladder Networkscited by 246
  18. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  19. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  20. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  21. 2020Does label smoothing mitigate label noise?cited by 204
  22. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  23. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  24. 2018Learning to Learn from Noisy Labeled Datacited by 160
  25. 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
  26. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 147
  27. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  28. 2019Deep Self-Learning From Noisy Labelscited by 122
  29. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
  30. 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
  31. 2020A Second-Order Approach to Learning with Instance-Dependent Label Noisecited by 90
  32. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  33. 2020Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noisecited by 82
  34. 2021Jo-SRC: A Contrastive Approach for Combating Noisy Labelscited by 80
  35. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  36. 2020When Optimizing f-divergence is Robust with Label Noisecited by 44
  37. 2018A Semi-Supervised Two-Stage Approach to Learning from Noisy Labelscited by 29
  38. 2020Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgettingcited by 28

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 0; 2026: 3.

5 papers.

  1. 2023Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discoverycited by 16
  2. 2024Online Continuous Generalized Category Discoverycited by 5
  3. 2026Combating Noisy Labels through Fostering Self- and Neighbor-Consistencycited by 0
  4. 2026Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learningcited by 0
  5. 2026On Revisiting Entropy for Identifying Mislabeled Imagescited by 0