Robust Long-Tailed Learning under Label Noise
- URL: http://arxiv.org/abs/2108.11569v1
- Date: Thu, 26 Aug 2021 03:45:00 GMT
- Title: Robust Long-Tailed Learning under Label Noise
- Authors: Tong Wei and Jiang-Xin Shi and Wei-Wei Tu and Yu-Feng Li
- Abstract summary: This work investigates the label noise problem under long-tailed label distribution.
We propose a robust framework,algo, that realizes noise detection for long-tailed learning.
Our framework can naturally leverage semi-supervised learning algorithms to further improve the generalisation.
- Score: 50.00837134041317
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Long-tailed learning has attracted much attention recently, with the goal of
improving generalisation for tail classes. Most existing works use supervised
learning without considering the prevailing noise in the training dataset. To
move long-tailed learning towards more realistic scenarios, this work
investigates the label noise problem under long-tailed label distribution. We
first observe the negative impact of noisy labels on the performance of
existing methods, revealing the intrinsic challenges of this problem. As the
most commonly used approach to cope with noisy labels in previous literature,
we then find that the small-loss trick fails under long-tailed label
distribution. The reason is that deep neural networks cannot distinguish
correctly-labeled and mislabeled examples on tail classes. To overcome this
limitation, we establish a new prototypical noise detection method by designing
a distance-based metric that is resistant to label noise. Based on the above
findings, we propose a robust framework,~\algo, that realizes noise detection
for long-tailed learning, followed by soft pseudo-labeling via both label
smoothing and diverse label guessing. Moreover, our framework can naturally
leverage semi-supervised learning algorithms to further improve the
generalisation. Extensive experiments on benchmark and real-world datasets
demonstrate the superiority of our methods over existing baselines. In
particular, our method outperforms DivideMix by 3\% in test accuracy. Source
code will be released soon.
Related papers
- Learning from Noisy Labels for Long-tailed Data via Optimal Transport [2.8821062918162146]
We propose a novel approach to manage data characterized by both long-tailed distributions and noisy labels.
We employ optimal transport strategies to generate pseudo-labels for the noise set in a semi-supervised training manner.
arXiv Detail & Related papers (2024-08-07T14:15:18Z) - 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) - ERASE: Error-Resilient Representation Learning on Graphs for Label Noise
Tolerance [53.73316938815873]
We propose a method called ERASE (Error-Resilient representation learning on graphs for lAbel noiSe tolerancE) to learn representations with error tolerance.
ERASE combines prototype pseudo-labels with propagated denoised labels and updates representations with error resilience.
Our method can outperform multiple baselines with clear margins in broad noise levels and enjoy great scalability.
arXiv Detail & Related papers (2023-12-13T17:59:07Z) - Co-Learning Meets Stitch-Up for Noisy Multi-label Visual Recognition [70.00984078351927]
This paper focuses on reducing noise based on some inherent properties of multi-label classification and long-tailed learning under noisy cases.
We propose a Stitch-Up augmentation to synthesize a cleaner sample, which directly reduces multi-label noise.
A Heterogeneous Co-Learning framework is further designed to leverage the inconsistency between long-tailed and balanced distributions.
arXiv Detail & Related papers (2023-07-03T09:20:28Z) - Label-Noise Learning with Intrinsically Long-Tailed Data [65.41318436799993]
We propose a learning framework for label-noise learning with intrinsically long-tailed data.
Specifically, we propose two-stage bi-dimensional sample selection (TABASCO) to better separate clean samples from noisy samples.
arXiv Detail & Related papers (2022-08-21T07:47:05Z) - Towards Harnessing Feature Embedding for Robust Learning with Noisy
Labels [44.133307197696446]
The memorization effect of deep neural networks (DNNs) plays a pivotal role in recent label noise learning methods.
We propose a novel feature embedding-based method for deep learning with label noise, termed LabEl NoiseDilution (LEND)
arXiv Detail & Related papers (2022-06-27T02:45:09Z) - Learning to Aggregate and Refine Noisy Labels for Visual Sentiment
Analysis [69.48582264712854]
We propose a robust learning method to perform robust visual sentiment analysis.
Our method relies on an external memory to aggregate and filter noisy labels during training.
We establish a benchmark for visual sentiment analysis with label noise using publicly available datasets.
arXiv Detail & Related papers (2021-09-15T18:18:28Z) - Label Noise Types and Their Effects on Deep Learning [0.0]
In this work, we provide a detailed analysis of the effects of different kinds of label noise on learning.
We propose a generic framework to generate feature-dependent label noise, which we show to be the most challenging case for learning.
For the ease of other researchers to test their algorithms with noisy labels, we share corrupted labels for the most commonly used benchmark datasets.
arXiv Detail & Related papers (2020-03-23T18:03:39Z)
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.