ARNet: Automatic Refinement Network for Noisy Partial Label Learning
- URL: http://arxiv.org/abs/2211.04774v2
- Date: Thu, 10 Nov 2022 04:24:21 GMT
- Title: ARNet: Automatic Refinement Network for Noisy Partial Label Learning
- Authors: Zheng Lian, Mingyu Xu, Lan Chen, Licai Sun, Bin Liu, Jianhua Tao
- Abstract summary: We propose a novel framework called "Automatic Refinement Network (ARNet)"
Our method consists of multiple rounds. In each round, we purify the noisy samples through two key modules, i.e., noisy sample detection and label correction.
We prove that our method is able to reduce the noise level of the dataset and eventually approximate the Bayes optimal.
- Score: 41.577081851679765
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Partial label learning (PLL) is a typical weakly supervised learning, where
each sample is associated with a set of candidate labels. The basic assumption
of PLL is that the ground-truth label must reside in the candidate set.
However, this assumption may not be satisfied due to the unprofessional
judgment of the annotators, thus limiting the practical application of PLL. In
this paper, we relax this assumption and focus on a more general problem, noisy
PLL, where the ground-truth label may not exist in the candidate set. To
address this challenging problem, we further propose a novel framework called
"Automatic Refinement Network (ARNet)". Our method consists of multiple rounds.
In each round, we purify the noisy samples through two key modules, i.e., noisy
sample detection and label correction. To guarantee the performance of these
modules, we start with warm-up training and automatically select the
appropriate correction epoch. Meanwhile, we exploit data augmentation to
further reduce prediction errors in ARNet. Through theoretical analysis, we
prove that our method is able to reduce the noise level of the dataset and
eventually approximate the Bayes optimal classifier. To verify the
effectiveness of ARNet, we conduct experiments on multiple benchmark datasets.
Experimental results demonstrate that our ARNet is superior to existing
state-of-the-art approaches in noisy PLL. Our code will be made public soon.
Related papers
- Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning [55.4510979153023]
In partial label learning (PLL), each instance is associated with a set of candidate labels among which only one is ground-truth.
To help these mislabeled samples "appeal," we propose the first appeal-based framework.
arXiv Detail & Related papers (2023-12-18T09:09:52Z) - ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label
Learning [46.53885746394252]
Noisy partial label learning is an important branch of weakly supervised learning.
Most of the existing works attempt to detect noisy samples and estimate the ground-truth label for each noisy sample.
We propose a novel framework for noisy with theoretical guarantees, called Adjusting Labeling Mechanism (ALIM)''
It aims to reduce the negative impact of detection errors by trading off the initial candidate set and model outputs.
arXiv Detail & Related papers (2023-01-28T03:42:53Z) - Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels [56.81761908354718]
We propose a novel theoretically guaranteed clean sample selection framework for learning with noisy labels.
Knockoffs-SPR can be regarded as a sample selection module for a standard supervised training pipeline.
We further combine it with a semi-supervised algorithm to exploit the support of noisy data as unlabeled data.
arXiv Detail & Related papers (2023-01-02T07:13:28Z) - Class Prototype-based Cleaner for Label Noise Learning [73.007001454085]
Semi-supervised learning methods are current SOTA solutions to the noisy-label learning problem.
We propose a simple yet effective solution, named textbfClass textbfPrototype-based label noise textbfCleaner.
arXiv Detail & Related papers (2022-12-21T04:56:41Z) - Progressive Purification for Instance-Dependent Partial Label Learning [37.65717805892473]
Partial label learning (PLL) aims to train multiclass classifiers from the examples each annotated with a set of candidate labels where a fixed but unknown candidate label is correct.
The candidate labels are always instance-dependent in practice and there is no theoretical guarantee that the model trained on the instance-dependent examples can converge to an ideal one.
In this paper, a theoretically grounded and practically effective approach named POP, i.e. PrOgressive Purification, is proposed. Specifically, POP updates the learning model and purifies each candidate label set progressively in every epoch.
arXiv Detail & Related papers (2022-06-02T02:07:12Z) - Scalable Penalized Regression for Noise Detection in Learning with Noisy
Labels [44.79124350922491]
We propose using a theoretically guaranteed noisy label detection framework to detect and remove noisy data for Learning with Noisy Labels (LNL)
Specifically, we design a penalized regression to model the linear relation between network features and one-hot labels.
To make the framework scalable to datasets that contain a large number of categories and training data, we propose a split algorithm to divide the whole training set into small pieces.
arXiv Detail & Related papers (2022-03-15T11:09:58Z) - Few-Shot Partial-Label Learning [25.609766770479265]
Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class by training on overly-annotated samples.
Existing few-shot learning algorithms assume precise labels of the support set; as such, irrelevant labels may seriously mislead the meta-learner.
In this paper, we introduce an approach called FsPLL (Few-shot image learning)
arXiv Detail & Related papers (2021-06-02T07:03:54Z) - Provably Consistent Partial-Label Learning [120.4734093544867]
Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels.
In this paper, we propose the first generation model of candidate label sets, and develop two novel methods that are guaranteed to be consistent.
Experiments on benchmark and real-world datasets validate the effectiveness of the proposed generation model and two methods.
arXiv Detail & Related papers (2020-07-17T12:19:16Z)
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.