When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method

• URL: http://arxiv.org/abs/2211.10955v3
• Date: Tue, 7 Nov 2023 04:51:00 GMT
• Title: When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method
• Authors: Manyi Zhang, Xuyang Zhao, Jun Yao, Chun Yuan, Weiran Huang
• Abstract summary: Real-world datasets are both noisily labeled and class-imbalanced. We propose a representation calibration method RCAL. We derive theoretical results to discuss the effectiveness of our representation calibration.
• Score: 40.25499257944916
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world large-scale datasets are both noisily labeled and class-imbalanced. The issues seriously hurt the generalization of trained models. It is hence significant to address the simultaneous incorrect labeling and class-imbalance, i.e., the problem of learning with noisy labels on long-tailed data. Previous works develop several methods for the problem. However, they always rely on strong assumptions that are invalid or hard to be checked in practice. In this paper, to handle the problem and address the limitations of prior works, we propose a representation calibration method RCAL. Specifically, RCAL works with the representations extracted by unsupervised contrastive learning. We assume that without incorrect labeling and class imbalance, the representations of instances in each class conform to a multivariate Gaussian distribution, which is much milder and easier to be checked. Based on the assumption, we recover underlying representation distributions from polluted ones resulting from mislabeled and class-imbalanced data. Additional data points are then sampled from the recovered distributions to help generalization. Moreover, during classifier training, representation learning takes advantage of representation robustness brought by contrastive learning, which further improves the classifier performance. We derive theoretical results to discuss the effectiveness of our representation calibration. Experiments on multiple benchmarks justify our claims and confirm the superiority of the proposed method.

Related papers

• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition [37.62659619941791]
  We study the problem of long-tailed visual recognition from the perspective of feature level. Two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead. Experiments conducted on benchmark datasets demonstrate the superior performance of the proposed method over the state-of-the-art ones.
  arXiv  Detail & Related papers  (2023-05-18T02:06:06Z)
• Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibration [18.59803726676361]
  Instance-dependent label noise is realistic but rather challenging, where the label-corruption process depends on instances directly. It causes a severe distribution shift between the distributions of training and test data, which impairs the generalization of trained models. In this paper, to address the distribution shift in learning with instance-dependent label noise, a dynamic distribution-calibration strategy is adopted.
  arXiv  Detail & Related papers  (2022-10-11T03:50:52Z)
• Learning to Adapt Classifier for Imbalanced Semi-supervised Learning [38.434729550279116]
  Pseudo-labeling has proven to be a promising semi-supervised learning (SSL) paradigm. Existing pseudo-labeling methods commonly assume that the class distributions of training data are balanced. In this work, we investigate pseudo-labeling under imbalanced semi-supervised setups.
  arXiv  Detail & Related papers  (2022-07-28T02:15:47Z)
• Throwing Away Data Improves Worst-Class Error in Imbalanced Classification [36.91428748713018]
  Class imbalances pervade classification problems, yet their treatment differs in theory and practice. We take on the challenge of developing learning theory able to describe the worst-class error of classifiers over linearly-separable data.
  arXiv  Detail & Related papers  (2022-05-23T23:43:18Z)
• Relieving Long-tailed Instance Segmentation via Pairwise Class Balance [85.53585498649252]
  Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. We propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences.
  arXiv  Detail & Related papers  (2022-01-08T07:48:36Z)
• PLM: Partial Label Masking for Imbalanced Multi-label Classification [59.68444804243782]
  Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. We propose a method, Partial Label Masking (PLM), which utilizes this ratio during training. Our method achieves strong performance when compared to existing methods on both multi-label (MultiMNIST and MSCOCO) and single-label (imbalanced CIFAR-10 and CIFAR-100) image classification datasets.
  arXiv  Detail & Related papers  (2021-05-22T18:07:56Z)
• Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces [64.23172847182109]
  We show that different negative sampling schemes implicitly trade-off performance on dominant versus rare labels. We provide a unified means to explicitly tackle both sampling bias, arising from working with a subset of all labels, and labeling bias, which is inherent to the data due to label imbalance.
  arXiv  Detail & Related papers  (2021-05-12T15:40:13Z)
• Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
  We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers. We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model. Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
  arXiv  Detail & Related papers  (2020-06-22T21:12:31Z)

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.