Robust Classification with Noisy Labels Based on Posterior Maximization

• URL: http://arxiv.org/abs/2504.06805v1
• Date: Wed, 09 Apr 2025 11:52:51 GMT
• Title: Robust Classification with Noisy Labels Based on Posterior Maximization
• Authors: Nicola Novello, Andrea M. Tonello,
• Abstract summary: In this paper, we investigate the robustness to label noise of an $f$-divergence-based class of objective functions recently proposed for supervised classification.<n>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.
• Score: 4.550290285002704
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning [6.68999525326685]
  Learning from noisy labels (LNL) aims to train high-performance deep models using noisy datasets.<n>We propose a novel noisy meta label correction framework STCT, which counterintuitively uses noisy data to correct label noise.<n> STCT achieves 96.9% label correction and 95.2% classification performance on CIFAR-10 with 80% symmetric noise.
  arXiv  Detail & Related papers  (2025-02-22T05:58:01Z)
• Extracting Clean and Balanced Subset for Noisy Long-tailed Classification [66.47809135771698]
  We develop a novel pseudo labeling method using class prototypes from the perspective of distribution matching. By setting a manually-specific probability measure, we can reduce the side-effects of noisy and long-tailed data simultaneously. Our method can extract this class-balanced subset with clean labels, which brings effective performance gains for long-tailed classification with label noise.
  arXiv  Detail & Related papers  (2024-04-10T07:34:37Z)
• Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels [61.97359362447732]
  Learning from noisy labels is an important and long-standing problem in machine learning for real applications. In this paper, we reformulate the label-noise problem from a generative-model perspective. Our model achieves new state-of-the-art (SOTA) results on all the standard real-world benchmark datasets.
  arXiv  Detail & Related papers  (2023-05-31T03:01:36Z)
• Deep Learning is Provably Robust to Symmetric Label Noise [20.496591498468778]
  We show that certain deep neural networks (DNNs) can tolerate massive symmetric label noise up to the information-theoretic threshold. We conjecture that for general label noise, mitigation strategies that make use of the noisy data will outperform those that ignore the noisy data.
  arXiv  Detail & Related papers  (2022-10-26T23:41:17Z)
• S3: Supervised Self-supervised Learning under Label Noise [53.02249460567745]
  In this paper we address the problem of classification in the presence of label noise. In the heart of our method is a sample selection mechanism that relies on the consistency between the annotated label of a sample and the distribution of the labels in its neighborhood in the feature space. Our method significantly surpasses previous methods on both CIFARCIFAR100 with artificial noise and real-world noisy datasets such as WebVision and ANIMAL-10N.
  arXiv  Detail & Related papers  (2021-11-22T15:49:20Z)
• Rethinking Pseudo Labels for Semi-Supervised Object Detection [84.697097472401]
  We introduce certainty-aware pseudo labels tailored for object detection. We dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem. Our approach improves supervised baselines by up to 10% AP using only 1-10% labeled data from COCO.
  arXiv  Detail & Related papers  (2021-06-01T01:32:03Z)
• Towards Robustness to Label Noise in Text Classification via Noise Modeling [7.863638253070439]
  Large datasets in NLP suffer from noisy labels, due to erroneous automatic and human annotation procedures. We study the problem of text classification with label noise, and aim to capture this noise through an auxiliary noise model over the classifier.
  arXiv  Detail & Related papers  (2021-01-27T05:41:57Z)
• Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model [80.91927573604438]
  This paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness.
  arXiv  Detail & Related papers  (2021-01-14T05:43:51Z)
• A Second-Order Approach to Learning with Instance-Dependent Label Noise [58.555527517928596]
  The presence of label noise often misleads the training of deep neural networks. We show that the errors in human-annotated labels are more likely to be dependent on the difficulty levels of tasks.
  arXiv  Detail & Related papers  (2020-12-22T06:36:58Z)
• Multi-Objective Interpolation Training for Robustness to Label Noise [17.264550056296915]
  We show that standard supervised contrastive learning degrades in the presence of label noise. We propose a novel label noise detection method that exploits the robust feature representations learned via contrastive learning. Experiments on synthetic and real-world noise benchmarks demonstrate that MOIT/MOIT+ achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2020-12-08T15:01:54Z)
• When Optimizing $f$-divergence is Robust with Label Noise [10.452709936265274]
  We show when maximizing a properly defined $f$-divergence measure with respect to a classifier's predictions and the supervised labels is robust with label noise. We derive a nice decoupling property for a family of $f$-divergence measures when label noise presents, where the divergence is shown to be a linear combination of the variational difference defined on the clean distribution and a bias term introduced due to the noise.
  arXiv  Detail & Related papers  (2020-11-07T04:31:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.