mlsanityData to 7 Oct 2026

Deep k-NN for Noisy Labels

arXiv 2004.12289 ↗First posted 26 Apr 2020cs.LG stat.MLcited by 55

Not on the map. Why?

Abstract (arXiv)

Modern machine learning models are often trained on examples with noisy labels that hurt performance and are hard to identify. In this paper, we provide an empirical study showing that a simple k-nearest neighbor-based filtering approach on the logit layer of a preliminary model can remove mislabeled training data and produce more accurate models than many recently proposed methods. We also provide new statistical guarantees into its efficacy.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 11; 2023: 9; 2024: 8; 2025: 2; 2026: 8.

55 papers.

Sort:

By area:

  1. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 151
  2. 2021Deep Learning Through the Lens of Example Difficultycited by 139
  3. 2021FINE Samples for Learning with Noisy Labelscited by 82
  4. 2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
  5. 2021Detecting Corrupted Labels Without Training a Model to Predictcited by 57
  6. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  7. 2022Identifiability of Label Noise Transition Matrixcited by 34
  8. 2022Neighborhood Collective Estimation for Noisy Label Identification and Correctioncited by 22
  9. 2022From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Modelcited by 21
  10. 2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
  11. 2023CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labelscited by 17
  12. 2023AQuA: A Benchmarking Tool for Label Quality Assessmentcited by 16
38 more
  1. 2024CLIPCleaner: Cleaning Noisy Labels with CLIPcited by 16
  2. 2021Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Imagescited by 13
  3. 2021SSR: An Efficient and Robust Framework for Learning with Unknown Label Noisecited by 13
  4. 2022Machine Learning with Confidential Computing: A Systematization of Knowledgecited by 13
  5. 2023DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modelingcited by 10
  6. 2022BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classificationcited by 9
  7. 2023VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Modelscited by 9
  8. 2021Locally Adaptive Label Smoothing for Predictive Churncited by 7
  9. 2022Bootstrapping the Relationship Between Images and Their Clean and Noisy Labelscited by 7
  10. 2024LEMoN: Label Error Detection using Multimodal Neighborscited by 6
  11. 2024Integrating kNN with Foundation Models for Adaptable and Privacy-Aware Image Classificationcited by 5
  12. 2024An Embedding is Worth a Thousand Noisy Labelscited by 5
  13. 2021ASK: Adversarial Soft k-Nearest Neighbor Attack and Defensecited by 4
  14. 2023Learning with Noisy Labels through Learnable Weighting and Centroid Similaritycited by 4
  15. 2024Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learningcited by 4
  16. 2021Multi-Branch Deep Radial Basis Function Networks for Facial Emotion Recognitioncited by 3
  17. 2023CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypescited by 3
  18. 2021Label Smoothed Embedding Hypothesis for Out-of-Distribution Detectioncited by 1
  19. 2021Active Coveringcited by 1
  20. 2022Context-based Virtual Adversarial Training for Text Classification with Noisy Labelscited by 1
  21. 2022New Metric Formulas that Include Measurement Errors in Machine Learning for Natural Sciencescited by 1
  22. 2022Denoising after Entropy-based Debiasing A Robust Training Method for Dataset Bias with Noisy Labelscited by 1
  23. 2023CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognitioncited by 1
  24. 2023Systematic Testing of the Data-Poisoning Robustness of KNNcited by 1
  25. 2023LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labelscited by 1
  26. 2024Robust Noisy Label Learning via Two-Stream Sample Distillationcited by 1
  27. 2024Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoderscited by 1
  28. 2024Mislabeled examples detection viewed as probing machine learning models: concepts, survey and extensive benchmarkcited by 1
  29. 2026Model-Agnostic Meta Learning for Class Imbalance Adaptationcited by 1
  30. 2026An Adaptive Data cleaning Framework for Noisy Label Detectioncited by 1
  31. 2021INN: A Method Identifying Clean-annotated Samples via Consistency Effect in Deep Neural Networkscited by 0
  32. 2021kNet: A Deep kNN Network To Handle Label Noisecited by 0
  33. 2021Deep Adversarially-Enhanced k-Nearest Neighborscited by 0
  34. 2021Disjoint Contrastive Regression Learning for Multi-Sourced Annotationscited by 0
  35. 2022Towards Harnessing Feature Embedding for Robust Learning with Noisy Labelscited by 0
  36. 2025A Prototype-Guided Coarse Annotations Refining Approach for Whole Slide Imagescited by 0
  37. 2025Detecting and Rectifying Noisy Labels: A Similarity-based Approachcited by 0
  38. 2026An assessment of data-centric methods for label noise identification in remote sensing data setscited by 0

50 most cited of 55 All 55 (JSON)