# Learning from Noisy Labels with Decoupled Meta Label Purifier

arXiv: https://arxiv.org/abs/2302.06810 · HTML: https://mlsanity.com/paper/2302.06810/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 14 Feb 2023.

## Builds on (most cited first, 30 of 30)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Training Deep Neural Networks on Noisy Labels with Bootstrapping](https://mlsanity.com/paper/1412.6596/) (2014)
- [Joint Optimization Framework for Learning with Noisy Labels](https://mlsanity.com/paper/1803.11364/) (2018)
- [Identifying Mislabeled Data using the Area Under the Margin Ranking](https://mlsanity.com/paper/2001.10528/) (2020)
- [Probabilistic End-to-end Noise Correction for Learning with Noisy Labels](https://mlsanity.com/paper/1903.07788/) (2019)
- [Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels](https://mlsanity.com/paper/1905.05040/) (2019)
- [Learning to Learn from Noisy Labeled Data](https://mlsanity.com/paper/1812.05214/) (2018)
- [Deep Self-Learning From Noisy Labels](https://mlsanity.com/paper/1908.02160/) (2019)
- [Selective-Supervised Contrastive Learning with Noisy Labels](https://mlsanity.com/paper/2203.04181/) (2022)
- [Meta Label Correction for Noisy Label Learning](https://mlsanity.com/paper/1911.03809/) (2019)
- [Multi-Objective Interpolation Training for Robustness to Label Noise](https://mlsanity.com/paper/2012.04462/) (2020)
- [Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels](https://mlsanity.com/paper/2103.13646/) (2021)
- [Learning to Purify Noisy Labels via Meta Soft Label Corrector](https://mlsanity.com/paper/2008.00627/) (2020)
- [Faster Meta Update Strategy for Noise-Robust Deep Learning](https://mlsanity.com/paper/2104.15092/) (2021)
- [Contrastive Learning Improves Model Robustness Under Label Noise](https://mlsanity.com/paper/2104.08984/) (2021)
- [Meta Soft Label Generation for Noisy Labels](https://mlsanity.com/paper/2007.05836/) (2020)
- [Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling](https://mlsanity.com/paper/2208.10683/) (2022)

## Built on by (most cited first, 21 of 21)

- [Mitigating Label Noise through Data Ambiguation](https://mlsanity.com/paper/2305.13764/) (2023)
- [Foster Adaptivity and Balance in Learning with Noisy Labels](https://mlsanity.com/paper/2407.02778/) (2024)
- [Fine tuning Pre trained Models for Robustness Under Noisy Labels](https://mlsanity.com/paper/2310.17668/) (2023)
- [De-Confusing Pseudo-Labels in Source-Free Domain Adaptation](https://mlsanity.com/paper/2401.01650/) (2024)
- [Learning with Noisy Labels through Learnable Weighting and Centroid Similarity](https://mlsanity.com/paper/2303.09470/) (2023)
- [FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation](https://mlsanity.com/paper/2601.22249/) (2026)
- [Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection](https://mlsanity.com/paper/2306.07215/) (2023)
- [Meta-Learn Unimodal Signals with Weak Supervision for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2408.16029/) (2024)
- [Combating Semantic Contamination in Learning with Label Noise](https://mlsanity.com/paper/2412.11620/) (2024)
- [AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2608.29081/) (2026)
- [CoLafier: Collaborative Noisy Label Purifier With Local Intrinsic Dimensionality Guidance](https://mlsanity.com/paper/2401.05458/) (2024)
- [A Multi-module Robust Method for Transient Stability Assessment against False Label Injection Cyberattacks](https://mlsanity.com/paper/2406.06744/) (2024)
- [Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning](https://mlsanity.com/paper/2502.16104/) (2025)
- [Not All Pixels Are Equal: Pixel-wise Meta-Learning for Medical Segmentation with Noisy Labels](https://mlsanity.com/paper/2511.18894/) (2025)
- [Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels](https://mlsanity.com/paper/2603.13894/) (2026)
- [BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization](https://mlsanity.com/paper/2605.10288/) (2026)
- [MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement](https://mlsanity.com/paper/2605.16081/) (2026)
- [Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learning](https://mlsanity.com/paper/2605.17833/) (2026)
- [Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets](https://mlsanity.com/paper/2606.29837/) (2026)
- [Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels](https://mlsanity.com/paper/2607.17857/) (2026)
- [Stop Replacing Noise with Noise: Two-Source Reliability Assessment for Label Correction and Sample Reweighting in Label-Noise Learning](https://mlsanity.com/paper/2608.03432/) (2026)

## Abstract (arXiv)

Training deep neural networks(DNN) with noisy labels is challenging since DNN can easily memorize inaccurate labels, leading to poor generalization ability. Recently, the meta-learning based label correction strategy is widely adopted to tackle this problem via identifying and correcting potential noisy labels with the help of a small set of clean validation data. Although training with purified labels can effectively improve performance, solving the meta-learning problem inevitably involves a nested loop of bi-level optimization between model weights and hyper-parameters (i.e., label distribution). As compromise, previous methods resort to a coupled learning process with alternating update. In this paper, we empirically find such simultaneous optimization over both model weights and label distribution can not achieve an optimal routine, consequently limiting the representation ability of backbone and accuracy of corrected labels. From this observation, a novel multi-stage label purifier named DMLP is proposed. DMLP decouples the label correction process into label-free representation learning and a simple meta label purifier. In this way, DMLP can focus on extracting discriminative feature and label correction in two distinctive stages. DMLP is a plug-and-play label purifier, the purified labels can be directly reused in naive end-to-end network retraining or other robust learning methods, where state-of-the-art results are obtained on several synthetic and real-world noisy datasets, especially under high noise levels.