Robust Classification with Noisy Labels Based on Posterior Maximization
Not on the map. Why?
Abstract (arXiv)
Designing objective functions robust to label noise is crucial for real-world classification algorithms. In this paper, we investigate the robustness to label noise of an f-divergence-based class of objective functions recently proposed for supervised classification, herein referred to as f-PML. We show that, in the presence of label noise, any of the f-PML objective functions can be corrected to obtain a neural network that is equal to the one learned with the clean dataset. Additionally, we propose an alternative and novel correction approach that, during the test phase, refines the posterior estimated by the neural network trained in the presence of label noise. Then, we demonstrate that, even if the considered f-PML objective functions are not symmetric, they are robust to symmetric label noise for any choice of f-divergence, without the need for any correction approach. This allows us to prove that the cross-entropy, which belongs to the f-PML class, is robust to symmetric label noise. Finally, we show that such a class of objective functions can be used together with refined training strategies, achieving competitive performance against state-of-the-art techniques of classification with label noise.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 53 of its 72 references that are in the map. First posted on arXiv 9 Apr 2025.
Builds on
53 of 72 references.
References · 53
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
- 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
- 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
- 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
- 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
- 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
- 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
38 more
- 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
- 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
- 2019On Mutual Information Maximization for Representation Learningcited by 316
- 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
- 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
- 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
- 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 261
- 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
- 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 256
- 2018Formal Limitations on the Measurement of Mutual Informationcited by 189
- 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
- 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
- 2018Learning to Learn from Noisy Labeled Datacited by 160
- 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
- 2019NLNL: Negative Learning for Noisy Labelscited by 151
- 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
- 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
- 2020Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Taskscited by 138
- 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
- 2022Robust Training under Label Noise by Over-parameterizationcited by 93
- 2017Learning from Complementary Labelscited by 88
- 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
- 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
- 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
- 2021Asymmetric Loss Functions for Learning with Noisy Labelscited by 46
- 2020When Optimizing f-divergence is Robust with Label Noisecited by 44
- 2022Mitigating Memorization of Noisy Labels by Clipping the Model Predictioncited by 40
- 2021Contrastive Learning Improves Model Robustness Under Label Noisecited by 36
- 2018Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithmscited by 27
- 2021Mitigating Memorization of Noisy Labels via Regularization between Representationscited by 26
- 2022On Learning Contrastive Representations for Learning with Noisy Labelscited by 21
- 2025Early Stopping Against Label Noise Without Validation Datacited by 21
- 2023Mutual Information Estimation via f-Divergence and Data Derangementscited by 17
- 2022PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labelscited by 10
- 2023Mitigating Label Noise through Data Ambiguationcited by 10
- 2024f-Divergence Based Classification: Beyond the Use of Cross-Entropycited by 8
- 2018Single-Label Multi-Class Image Classification by Deep Logistic Regressioncited by 6
- 2024Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learningcited by 4
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.