A Second-Order Approach to Learning with Instance-Dependent Label Noise

• URL: http://arxiv.org/abs/2012.11854v2
• Date: Tue, 30 Mar 2021 16:17:12 GMT
• Title: A Second-Order Approach to Learning with Instance-Dependent Label Noise
• Authors: Zhaowei Zhu, Tongliang Liu, Yang Liu
• Abstract summary: 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.
• Score: 58.555527517928596
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated labels are more likely to be dependent on the difficulty levels of tasks, resulting in settings with instance-dependent label noise. We first provide evidences that the heterogeneous instance-dependent label noise is effectively down-weighting the examples with higher noise rates in a non-uniform way and thus causes imbalances, rendering the strategy of directly applying methods for class-dependent label noise questionable. Built on a recent work peer loss [24], we then propose and study the potentials of a second-order approach that leverages the estimation of several covariance terms defined between the instance-dependent noise rates and the Bayes optimal label. We show that this set of second-order statistics successfully captures the induced imbalances. We further proceed to show that with the help of the estimated second-order statistics, we identify a new loss function whose expected risk of a classifier under instance-dependent label noise is equivalent to a new problem with only class-dependent label noise. This fact allows us to apply existing solutions to handle this better-studied setting. We provide an efficient procedure to estimate these second-order statistics without accessing either ground truth labels or prior knowledge of the noise rates. Experiments on CIFAR10 and CIFAR100 with synthetic instance-dependent label noise and Clothing1M with real-world human label noise verify our approach. Our implementation is available at https://github.com/UCSC-REAL/CAL.

Related papers

• Towards the Identifiability in Noisy Label Learning: A Multinomial Mixture Approach [37.32107678838193]
  Learning from noisy labels (LNL) plays a crucial role in deep learning. The most promising LNL methods rely on identifying clean-label samples from a dataset with noisy annotations. We propose a method that automatically generates additional noisy labels by estimating the noisy label distribution based on nearest neighbours.
  arXiv  Detail & Related papers  (2023-01-04T01:54:33Z)
• Instance-dependent Label Distribution Estimation for Learning with Label Noise [20.479674500893303]
  Noise transition matrix (NTM) estimation is a promising approach for learning with label noise. We propose an Instance-dependent Label Distribution Estimation (ILDE) method to learn from noisy labels for image classification. Our results indicate that the proposed ILDE method outperforms all competing methods, no matter whether the noise is synthetic or real noise.
  arXiv  Detail & Related papers  (2022-12-16T10:13:25Z)
• Neighborhood Collective Estimation for Noisy Label Identification and Correction [92.20697827784426]
  Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. Recent advances employ the predicted label distributions of individual samples to perform noise verification and noisy label correction, easily giving rise to confirmation bias. We propose Neighborhood Collective Estimation, in which the predictive reliability of a candidate sample is re-estimated by contrasting it against its feature-space nearest neighbors.
  arXiv  Detail & Related papers  (2022-08-05T14:47:22Z)
• 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)
• Open-set Label Noise Can Improve Robustness Against Inherent Label Noise [27.885927200376386]
  We show that open-set noisy labels can be non-toxic and even benefit the robustness against inherent noisy labels. We propose a simple yet effective regularization by introducing Open-set samples with Dynamic Noisy Labels (ODNL) into training.
  arXiv  Detail & Related papers  (2021-06-21T07:15:50Z)
• 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)
• Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels [98.13491369929798]
  We propose a framework called Class2Simi, which transforms data points with noisy class labels to data pairs with noisy similarity labels. Class2Simi is computationally efficient because not only this transformation is on-the-fly in mini-batches, but also it just changes loss on top of model prediction into a pairwise manner.
  arXiv  Detail & Related papers  (2020-06-14T07:55:32Z)
• NoiseRank: Unsupervised Label Noise Reduction with Dependence Models [11.08987870095179]
  We propose NoiseRank, for unsupervised label noise reduction using Markov Random Fields (MRF) We construct a dependence model to estimate the posterior probability of an instance being incorrectly labeled given the dataset, and rank instances based on their estimated probabilities. NoiseRank improves state-of-the-art classification on Food101-N (20% noise) and is effective on high noise Clothing-1M (40% noise)
  arXiv  Detail & Related papers  (2020-03-15T01:10:25Z)
• Confidence Scores Make Instance-dependent Label-noise Learning Possible [129.84497190791103]
  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. 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.
  arXiv  Detail & Related papers  (2020-01-11T16:15:41Z)

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.