Learning from Noisy Labels for Long-tailed Data via Optimal Transport
- URL: http://arxiv.org/abs/2408.03977v1
- Date: Wed, 7 Aug 2024 14:15:18 GMT
- Title: Learning from Noisy Labels for Long-tailed Data via Optimal Transport
- Authors: Mengting Li, Chuang Zhu,
- Abstract summary: 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.
- Score: 2.8821062918162146
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Noisy labels, which are common in real-world datasets, can significantly impair the training of deep learning models. However, recent adversarial noise-combating methods overlook the long-tailed distribution of real data, which can significantly harm the effect of denoising strategies. Meanwhile, the mismanagement of noisy labels further compromises the model's ability to handle long-tailed data. To tackle this issue, we propose a novel approach to manage data characterized by both long-tailed distributions and noisy labels. First, we introduce a loss-distance cross-selection module, which integrates class predictions and feature distributions to filter clean samples, effectively addressing uncertainties introduced by noisy labels and long-tailed distributions. Subsequently, we employ optimal transport strategies to generate pseudo-labels for the noise set in a semi-supervised training manner, enhancing pseudo-label quality while mitigating the effects of sample scarcity caused by the long-tailed distribution. We conduct experiments on both synthetic and real-world datasets, and the comprehensive experimental results demonstrate that our method surpasses current state-of-the-art methods. Our code will be available in the future.
Related papers
- Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition [50.61991746981703]
Current state-of-the-art LTSSL approaches rely on high-quality pseudo-labels for large-scale unlabeled data.
This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning.
We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels.
arXiv Detail & Related papers (2024-10-08T15:06:10Z) - 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) - Learning with Imbalanced Noisy Data by Preventing Bias in Sample
Selection [82.43311784594384]
Real-world datasets contain not only noisy labels but also class imbalance.
We propose a simple yet effective method to address noisy labels in imbalanced datasets.
arXiv Detail & Related papers (2024-02-17T10:34:53Z) - 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) - Learning with Noisy labels via Self-supervised Adversarial Noisy Masking [33.87292143223425]
We propose a novel training approach termed adversarial noisy masking.
It adaptively modulates the input data and label simultaneously, preventing the model to overfit noisy samples.
It is tested on both synthetic and real-world noisy datasets.
arXiv Detail & Related papers (2023-02-14T03:13:26Z) - Learning from Long-Tailed Noisy Data with Sample Selection and Balanced
Loss [8.71234615872208]
We propose a robust method for learning from long-tailed noisy data with sample selection and balanced loss.
Specifically, we separate the noisy training data into clean labeled set and unlabeled set with sample selection, and train the deep neural network in a semi-supervised manner.
arXiv Detail & Related papers (2022-11-20T08:48:34Z) - 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) - Robust Long-Tailed Learning under Label Noise [50.00837134041317]
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.
arXiv Detail & Related papers (2021-08-26T03:45:00Z) - Semi-supervised Long-tailed Recognition using Alternate Sampling [95.93760490301395]
Main challenges in long-tailed recognition come from the imbalanced data distribution and sample scarcity in its tail classes.
We propose a new recognition setting, namely semi-supervised long-tailed recognition.
We demonstrate significant accuracy improvements over other competitive methods on two datasets.
arXiv Detail & Related papers (2021-05-01T00:43:38Z)
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.