mlsanityData to 14 Oct 2026

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

arXiv 2212.01674 ↗First posted 3 Dec 2022cs.CV cs.AI cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization of noisy labels, called CrossSplit, which uses a pair of neural networks trained on two disjoint parts of the labelled dataset. CrossSplit combines two main ingredients: (i) Cross-split label correction. The idea is that, since the model trained on one part of the data cannot memorize example-label pairs from the other part, the training labels presented to each network can be smoothly adjusted by using the predictions of its peer network; (ii) Cross-split semi-supervised training. A network trained on one part of the data also uses the unlabeled inputs of the other part. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet and mini-WebVision datasets demonstrate that our method can outperform the current state-of-the-art in a wide range of noise ratios.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 35 of its 50 references that are in the map. First posted on arXiv 3 Dec 2022.

Builds on

35 of 50 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  6. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  7. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  8. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  9. 2017A Closer Look at Memorization in Deep Networkscited by 942
  10. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  11. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  12. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 460
23 more
  1. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  2. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  3. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
  4. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  5. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  6. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  7. 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 261
  8. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  9. 2017Decoupling "when to update" from "how to update"cited by 230
  10. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  11. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  12. 2017Learning from Noisy Labels with Distillationcited by 161
  13. 2018Learning to Learn from Noisy Labeled Datacited by 160
  14. 2021Deep Learning Through the Lens of Example Difficultycited by 141
  15. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  16. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  17. 2020Multi-Objective Interpolation Training for Robustness to Label Noisecited by 86
  18. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  19. 2021Joint Negative and Positive Learning for Noisy Labelscited by 34
  20. 2022SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labelscited by 24
  21. 2022Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classificationcited by 21
  22. 2021A Tale Of Two Long Tailscited by 19
  23. 2020Noisy Concurrent Training for Efficient Learning under Label Noisecited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 1; 2026: 4.

12 papers.

  1. 2023Discovering environments with XRMcited by 26
  2. 2024CLIPCleaner: Cleaning Noisy Labels with CLIPcited by 16
  3. 2023Learning with Noisy Labels through Learnable Weighting and Centroid Similaritycited by 4
  4. 2023Improve Noise Tolerance of Robust Loss via Noise-Awarenesscited by 3
  5. 2024Mislabeled examples detection viewed as probing machine learning models: concepts, survey and extensive benchmarkcited by 1
  6. 2024Combating Semantic Contamination in Learning with Label Noisecited by 1
  7. 2024Energy Guided smoothness to improve Robustness in Graph Classificationcited by 0
  8. 2025Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learningcited by 0
  9. 2026Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labelscited by 0
  10. 2026XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Spacecited by 0
  11. 2026Stop Replacing Noise with Noise: Two-Source Reliability Assessment for Label Correction and Sample Reweighting in Label-Noise Learningcited by 0
  12. 2026Selective Posterior Margin Regularization for Forward-Corrected Classificationcited by 0