mlsanityData to 14 Oct 2026

CNLL: A Semi-supervised Approach For Continual Noisy Label Learning

arXiv 2204.09881 ↗First posted 21 Apr 2022cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

The task of continual learning requires careful design of algorithms that can tackle catastrophic forgetting. However, the noisy label, which is inevitable in a real-world scenario, seems to exacerbate the situation. While very few studies have addressed the issue of continual learning under noisy labels, long training time and complicated training schemes limit their applications in most cases. In contrast, we propose a simple purification technique to effectively cleanse the online data stream that is both cost-effective and more accurate. After purification, we perform fine-tuning in a semi-supervised fashion that ensures the participation of all available samples. Training in this fashion helps us learn a better representation that results in state-of-the-art (SOTA) performance. Through extensive experimentation on 3 benchmark datasets, MNIST, CIFAR10 and CIFAR100, we show the effectiveness of our proposed approach. We achieve a 24.8% performance gain for CIFAR10 with 20% noise over previous SOTA methods. Our code is publicly available.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 59 of its 83 references that are in the map. First posted on arXiv 21 Apr 2022.

Builds on

59 of 83 references.

References · 59

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  6. 2016Progressive Neural Networkscited by 1,361
  7. 2017Continual Learning with Deep Generative Replaycited by 1,158
  8. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  9. 2018Experience Replay for Continual Learningcited by 1,095
  10. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  11. 2017A Closer Look at Memorization in Deep Networkscited by 942
  12. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
38 more
  1. 2019Large Scale Incremental Learningcited by 732
  2. 2017Lifelong Learning with Dynamically Expandable Networkscited by 694
  3. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  4. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  5. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  6. 2019Three scenarios for continual learningcited by 614
  7. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
  8. 2019Gradient based sample selection for online continual learningcited by 571
  9. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 521
  10. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  11. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  12. 2019On the Efficacy of Knowledge Distillationcited by 381
  13. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 379
  14. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
  15. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  16. 2019Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgettingcited by 302
  17. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  18. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  19. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 283
  20. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  21. 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 261
  22. 2018Learning without Memorizingcited by 250
  23. 2020Mnemonics Training: Multi-Class Incremental Learning without Forgettingcited by 221
  24. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  25. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  26. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  27. 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
  28. 2019Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learningcited by 182
  29. 2017Learning from Noisy Labels with Distillationcited by 161
  30. 2018Learning to Learn from Noisy Labeled Datacited by 160
  31. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  32. 2021Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningcited by 131
  33. 2018Memory Efficient Experience Replay for Streaming Learningcited by 128
  34. 2020Conditional Channel Gated Networks for Task-Aware Continual Learningcited by 115
  35. 2021Jo-SRC: A Contrastive Approach for Combating Noisy Labelscited by 80
  36. 2019Lifelong GAN: Continual Learning for Conditional Image Generationcited by 78
  37. 2020Imbalanced Continual Learning with Partitioning Reservoir Samplingcited by 72
  38. 2021Essentials for Class Incremental Learningcited by 57

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 1; 2026: 1.

8 papers.

  1. 2023SIESTA: Efficient Online Continual Learning with Sleepcited by 24
  2. 2024Enhancing Continual Learning in Visual Question Answering with Modality-Aware Feature Distillationcited by 7
  3. 2023CEFHRI: A Communication Efficient Federated Learning Framework for Recognizing Industrial Human-Robot Interactioncited by 3
  4. 2025ErrorEraser: Unlearning Data Bias for Improved Continual Learningcited by 3
  5. 2023URL: Combating Label Noise for Lung Nodule Malignancy Gradingcited by 2
  6. 2024May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labelscited by 2
  7. 2023Variational Self-Supervised Contrastive Learning Using Beta Divergencecited by 0
  8. 2026Reliable Replay through Spatial Coherence in Online Continual Learningcited by 0