mlsanityData to 7 Oct 2026

Confidence Scores Make Instance-dependent Label-noise Learning Possible

arXiv 2001.03772 ↗First posted 11 Jan 2020cs.LG stat.MLcited by 63

Not on the map. Why?

Abstract (arXiv)

In learning with noisy labels, for every instance, its label can randomly walk to other classes following a transition distribution which is named a noise model. Well-studied noise models are all instance-independent, namely, the transition depends only on the original label but not the instance itself, and thus they are less practical in the wild. Fortunately, methods based on instance-dependent noise have been studied, but most of them have to rely on strong assumptions on the noise models. To alleviate this issue, we introduce confidence-scored instance-dependent noise (CSIDN), where each instance-label pair is equipped with a confidence score. We find with the help of confidence scores, the transition distribution of each instance can be approximately estimated. Similarly to the powerful forward correction for instance-independent noise, we propose a novel instance-level forward correction for CSIDN. We demonstrate the utility and effectiveness of our method through multiple experiments under synthetic label noise and real-world unknown noise.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 11; 2023: 12; 2024: 13; 2025: 7; 2026: 6.

63 papers.

Sort:

By area:

  1. 2022Backdoor Defense via Decoupling the Training Processcited by 149
  2. 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
  3. 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
  4. 2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
  5. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  6. 2021Instance-dependent Label-noise Learning under a Structural Causal Modelcited by 50
  7. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  8. 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labelscited by 46
  9. 2022Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shiftcited by 38
  10. 2022Identifiability of Label Noise Transition Matrixcited by 34
  11. 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
  12. 2022From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Modelcited by 21
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. 2021Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noisecited by 18
  4. 2022Instance-Dependent Noisy Label Learning via Graphical Modellingcited by 17
  5. 2024Label-Noise Robust Diffusion Modelscited by 16
  6. 2021An Instance-Dependent Simulation Framework for Learning with Label Noisecited by 14
  7. 2024Don't drop your samples! Coherence-aware training benefits Conditional diffusioncited by 13
  8. 2021Tackling Instance-Dependent Label Noise via a Universal Probabilistic Modelcited by 12
  9. 2024Cost-Sensitive Learning to Defer to Multiple Experts with Workload Constraintscited by 12
  10. 2023DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modelingcited by 10
  11. 2022Instance-dependent Label Distribution Estimation for Learning with Label Noisecited by 9
  12. 2023VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Modelscited by 9
  13. 2024Foster Adaptivity and Balance in Learning with Noisy Labelscited by 9
  14. 2021Deep Classifiers with Label Noise Modeling and Distance Awarenesscited by 8
  15. 2021Learning with Proper Partial Labelscited by 8
  16. 2023Multi-annotator Deep Learning: A Probabilistic Framework for Classificationcited by 8
  17. 2024Trusted Multi-view Learning under Noisy Supervisioncited by 8
  18. 2022Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learningcited by 7
  19. 2022Label Noise-Robust Learning using a Confidence-Based Sieving Strategycited by 6
  20. 2024Mitigating Label Noise on Graph via Topological Sample Selectioncited by 6
  21. 2024Learning with Confidence: Training Better Classifiers from Soft Labelscited by 6
  22. 2022ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy Statecited by 5
  23. 2023Unified Risk Analysis for Weakly Supervised Learningcited by 5
  24. 2023Leveraging an Alignment Set in Tackling Instance-Dependent Label Noisecited by 4
  25. 2024Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learningcited by 4
  26. 2025Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinementcited by 4
  27. 2021Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimationcited by 3
  28. 2023Unsupervised Domain-agnostic Fake News Detection using Multi-modal Weak Signalscited by 3
  29. 2023FiFAR: A Fraud Detection Dataset for Learning to Defercited by 3
  30. 2024Learning Causal Transition Matrix for Instance-dependent Label Noisecited by 3
  31. 2025Enhanced Sample Selection with Confidence Tracking: Identifying Correctly Labeled yet Hard-to-Learn Samples in Noisy Datacited by 3
  32. 2022Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibrationcited by 2
  33. 2023Binary Classification with Instance and Label Dependent Label Noisecited by 2
  34. 2023Generating the Ground Truth: Synthetic Data for Soft Label and Label Noise Researchcited by 2
  35. 2024AlleNoise: large-scale text classification benchmark dataset with real-world label noisecited by 2
  36. 2026Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Predictioncited by 2
  37. 2024NoisyAG-News: A Benchmark for Addressing Instance-Dependent Noise in Text Classificationcited by 1
  38. 2024Learning with Instance-Dependent Noisy Labels by Anchor Hallucination and Hard Sample Label Correctioncited by 1

50 most cited of 63 All 63 (JSON)