mlsanityData to 7 Oct 2026

A Topological Filter for Learning with Label Noise

arXiv 2012.04835 ↗First posted 9 Dec 2020cs.CV cs.LGcited by 76

Not on the map. Why?

Abstract (arXiv)

Noisy labels can impair the performance of deep neural networks. To tackle this problem, in this paper, we propose a new method for filtering label noise. Unlike most existing methods relying on the posterior probability of a noisy classifier, we focus on the much richer spatial behavior of data in the latent representational space. By leveraging the high-order topological information of data, we are able to collect most of the clean data and train a high-quality model. Theoretically we prove that this topological approach is guaranteed to collect the clean data with high probability. Empirical results show that our method outperforms the state-of-the-arts and is robust to a broad spectrum of noise types and levels.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 14; 2023: 20; 2024: 11; 2025: 9; 2026: 5.

76 papers.

Sort:

By area:

  1. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  2. 2021FINE Samples for Learning with Noisy Labelscited by 82
  3. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  4. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  5. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  6. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  7. 2021Trigger Hunting with a Topological Prior for Trojan Detectioncited by 39
  8. 2021Topological Detection of Trojaned Neural Networkscited by 34
  9. 2022Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamicscited by 26
  10. 2021Cycle Representation Learning for Inductive Relation Predictioncited by 23
  11. 2022Neighborhood Collective Estimation for Noisy Label Identification and Correctioncited by 22
  12. 2023BatchNorm-based Weakly Supervised Video Anomaly Detectioncited by 22
38 more
  1. 2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
  2. 2023Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labelscited by 20
  3. 2023Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracycited by 20
  4. 2021A Tale Of Two Long Tailscited by 19
  5. 2022Identifying Hard Noise in Long-Tailed Sample Distributioncited by 19
  6. 2021Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noisecited by 18
  7. 2023Late Stopping: Avoiding Confidently Learning from Mislabeled Examplescited by 17
  8. 2024CLIPCleaner: Cleaning Noisy Labels with CLIPcited by 16
  9. 2022Scalable Penalized Regression for Noise Detection in Learning with Noisy Labelscited by 15
  10. 2023Rethinking Precision of Pseudo Label: Test-Time Adaptation via Complementary Learningcited by 14
  11. 2021SSR: An Efficient and Robust Framework for Learning with Unknown Label Noisecited by 13
  12. 2023Resurrecting Label Propagation for Graphs with Heterophily and Label Noisecited by 12
  13. 2024AFreeCA: Annotation-Free Counting for Allcited by 12
  14. 2023ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerancecited by 11
  15. 2022BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classificationcited by 9
  16. 2021Sample Prior Guided Robust Model Learning to Suppress Noisy Labelscited by 8
  17. 2022SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Trainingcited by 8
  18. 2024Noisy Label Processing for Classification: A Surveycited by 8
  19. 2024Generalizable Person Re-identification via Balancing Alignment and Uniformitycited by 8
  20. 2024LEMoN: Label Error Detection using Multimodal Neighborscited by 6
  21. 2022ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy Statecited by 5
  22. 2022A Survey of Dataset Refinement for Problems in Computer Vision Datasetscited by 5
  23. 2022Learning with Noisy Labels over Imbalanced Subpopulationscited by 5
  24. 2021Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awarenesscited by 4
  25. 2022Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videoscited by 4
  26. 2023Learning with Noisy Labels through Learnable Weighting and Centroid Similaritycited by 4
  27. 2025Sample Selection via Contrastive Fragmentation for Noisy Label Regressioncited by 4
  28. 2025Diffusion on Graph: Augmentation of Graph Structure for Node Classificationcited by 4
  29. 2021Approximating Instance-Dependent Noise via Instance-Confidence Embeddingcited by 3
  30. 2023Improve Noise Tolerance of Robust Loss via Noise-Awarenesscited by 3
  31. 2023MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labelscited by 3
  32. 2023CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypescited by 3
  33. 2024ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labelscited by 3
  34. 2024Learning Causal Transition Matrix for Instance-dependent Label Noisecited by 3
  35. 2025Active Learning with a Noisy Annotatorcited by 3
  36. 2025Enhanced Sample Selection with Confidence Tracking: Identifying Correctly Labeled yet Hard-to-Learn Samples in Noisy Datacited by 3
  37. 2021Detecting Label Noise via Leave-One-Out Cross-Validationcited by 2
  38. 2022On the Convergence of Optimizing Persistent-Homology-Based Lossescited by 2

50 most cited of 76 All 76 (JSON)