LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integration
Not on the map. Why?
Abstract (arXiv)
Learning with noisy labels (LNL) aims to train a high-performing model using a noisy dataset. We observe that noise for a given class often comes from a limited set of categories, yet many LNL methods overlook this. For example, an image mislabeled as a cheetah is more likely a leopard than a hippopotamus due to its visual similarity. Thus, we explore Learning with Noisy Labels with noise source Knowledge integration (LNL+K), which leverages knowledge about likely source(s) of label noise that is often provided in a dataset's meta-data. Integrating noise source knowledge boosts performance even in settings where LNL methods typically fail. For example, LNL+K methods are effective on datasets where noise represents the majority of samples, which breaks a critical premise of most methods developed for LNL. Our LNL+K methods can boost performance even when noise sources are estimated rather than extracted from meta-data. We provide several baseline LNL+K methods that integrate noise source knowledge into state-of-the-art LNL models that are evaluated across six diverse datasets and two types of noise, where we report gains of up to 23% compared to the unadapted methods. Critically, we show that LNL methods fail to generalize on some real-world datasets, even when adapted to integrate noise source knowledge, highlighting the importance of directly exploring LNL+K.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 47 of its 71 references that are in the map. First posted on arXiv 20 Jun 2023.
Builds on
47 of 71 references.
References · 47
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2022A ConvNet for the 2020scited by 3,579
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
- 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
- 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
- 2017A Closer Look at Memorization in Deep Networkscited by 942
- 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
- 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
- 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
- 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
- 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
35 more
- 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
- 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
- 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 261
- 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
- 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
- 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
- 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
- 2017Learning from Noisy Labels with Distillationcited by 161
- 2019Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networkscited by 159
- 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
- 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
- 2019Learning From Noisy Labels By Regularized Estimation Of Annotator Confusioncited by 127
- 2017Learning From Noisy Large-Scale Datasets With Minimal Supervisioncited by 115
- 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 113
- 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
- 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
- 2018Masking: A New Perspective of Noisy Supervisioncited by 93
- 2022Robust Training under Label Noise by Over-parameterizationcited by 93
- 2021FINE Samples for Learning with Noisy Labelscited by 82
- 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
- 2020A Topological Filter for Learning with Label Noisecited by 76
- 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
- 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
- 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
- 2021LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environmentcited by 40
- 2022Identifiability of Label Noise Transition Matrixcited by 34
- 2022Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalizationcited by 33
- 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
- 2018Label-Noise Robust Generative Adversarial Networkscited by 22
- 2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
- 2016Embracing Error to Enable Rapid Crowdsourcingcited by 15
- 2021SSR: An Efficient and Robust Framework for Learning with Unknown Label Noisecited by 13
- 2020P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributionscited by 7
- 2022Label Noise-Robust Learning using a Confidence-Based Sieving Strategycited by 6
- 2013Constructive Setting of the Density Ratio Estimation Problem and its Rigorous Solutioncited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.