mlsanityData to 7 Oct 2026

Part-dependent Label Noise: Towards Instance-dependent Label Noise

arXiv 2006.07836 ↗First posted 14 Jun 2020cs.LG stat.MLcited by 40

Not on the map. Why?

Abstract (arXiv)

Learning with the textitinstance-dependent label noise is challenging, because it is hard to model such real-world noise. Note that there are psychological and physiological evidences showing that we humans perceive instances by decomposing them into parts. Annotators are therefore more likely to annotate instances based on the parts rather than the whole instances, where a wrong mapping from parts to classes may cause the instance-dependent label noise. Motivated by this human cognition, in this paper, we approximate the instance-dependent label noise by exploiting textitpart-dependent label noise. Specifically, since instances can be approximately reconstructed by a combination of parts, we approximate the instance-dependent textittransition matrix for an instance by a combination of the transition matrices for the parts of the instance. The transition matrices for parts can be learned by exploiting anchor points (i.e., data points that belong to a specific class almost surely). Empirical evaluations on synthetic and real-world datasets demonstrate our method is superior to the state-of-the-art approaches for learning from the instance-dependent label noise.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 25; 2022: 9; 2023: 6.

40 papers.

Sort:

  1. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
  2. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
  3. 2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
  4. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
  5. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  6. 2021Instance-dependent Label-noise Learning under a Structural Causal Modelcited by 50
  7. 2022Understanding Robust Overfitting of Adversarial Training and Beyondcited by 50
  8. 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labelscited by 46
  9. 2021Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterioncited by 36
  10. 2022Identifiability of Label Noise Transition Matrixcited by 34
  11. 2022Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalizationcited by 33
  12. 2021Meta Discovery: Learning to Discover Novel Classes given Very Limited Datacited by 30
28 more
  1. 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
  2. 2023Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimizationcited by 29
  3. 2022Progressive Purification for Instance-Dependent Partial Label Learningcited by 23
  4. 2021Understanding Instance-Level Label Noise: Disparate Impacts and Treatmentscited by 22
  5. 2021Adaptive Sample Selection for Robust Learning under Label Noisecited by 20
  6. 2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
  7. 2021Removing Adversarial Noise in Class Activation Feature Spacecited by 18
  8. 2022Instance-Dependent Noisy Label Learning via Graphical Modellingcited by 17
  9. 2022Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labelscited by 16
  10. 2021Analysing the Noise Model Error for Realistic Noisy Label Datacited by 14
  11. 2021Tackling Instance-Dependent Label Noise via a Universal Probabilistic Modelcited by 12
  12. 2021Learning to Rectify for Robust Learning with Noisy Labelscited by 12
  13. 2021Model Generalization on COVID-19 Fake News Detectioncited by 11
  14. 2021On the Robustness of Monte Carlo Dropout Trained with Noisy Labelscited by 11
  15. 2023Counterfactual Prediction Under Outcome Measurement Errorcited by 10
  16. 2022Bootstrapping the Relationship Between Images and Their Clean and Noisy Labelscited by 7
  17. 2021Learning with Group Noisecited by 5
  18. 2021Confidence Adaptive Regularization for Deep Learning with Noisy Labelscited by 5
  19. 2021Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awarenesscited by 4
  20. 2021How Does Heterogeneous Label Noise Impact Generalization in Neural Nets?cited by 3
  21. 2021Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimationcited by 3
  22. 2023Binary Classification with Instance and Label Dependent Label Noisecited by 2
  23. 2021A Symmetric Loss Perspective of Reliable Machine Learningcited by 0
  24. 2021Generation and Analysis of Feature-Dependent Pseudo Noise for Training Deep Neural Networkscited by 0
  25. 2022Phenotyping with Positive Unlabelled Learning for Genome-Wide Association Studiescited by 0
  26. 2022A Study of Deep CNN Model with Labeling Noise Based on Granular-ball Computingcited by 0
  27. 2023biquality-learn: a Python library for Biquality Learningcited by 0
  28. 2023Multi-Label Noise Transition Matrix Estimation with Label Correlations: Theory and Algorithmcited by 0