# Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization

arXiv: https://arxiv.org/abs/2208.11351 · HTML: https://mlsanity.com/paper/2208.11351/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 24 Aug 2022.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [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)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (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)
- [Joint Optimization Framework for Learning with Noisy Labels](https://mlsanity.com/paper/1803.11364/) (2018)
- [Combating noisy labels by agreement: A joint training method with co-regularization](https://mlsanity.com/paper/2003.02752/) (2020)
- [Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise](https://mlsanity.com/paper/1802.05300/) (2018)
- [Are Anchor Points Really Indispensable in Label-Noise Learning?](https://mlsanity.com/paper/1906.00189/) (2019)
- [Does label smoothing mitigate label noise?](https://mlsanity.com/paper/2003.02819/) (2020)
- [SELF: Learning to Filter Noisy Labels with Self-Ensembling](https://mlsanity.com/paper/1910.01842/) (2019)
- [Learning from Noisy Labels with Distillation](https://mlsanity.com/paper/1703.02391/) (2017)
- [Learning with Instance-Dependent Label Noise: A Sample Sieve Approach](https://mlsanity.com/paper/2010.02347/) (2020)
- [Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates](https://mlsanity.com/paper/1910.03231/) (2019)
- [Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning](https://mlsanity.com/paper/2006.07805/) (2020)
- [Understanding and Improving Early Stopping for Learning with Noisy Labels](https://mlsanity.com/paper/2106.15853/) (2021)
- [Robust Bi-Tempered Logistic Loss Based on Bregman Divergences](https://mlsanity.com/paper/1906.03361/) (2019)
- [Learning with Bounded Instance- and Label-dependent Label Noise](https://mlsanity.com/paper/1709.03768/) (2017)
- [Part-dependent Label Noise: Towards Instance-dependent Label Noise](https://mlsanity.com/paper/2006.07836/) (2020)
- [Learning to Purify Noisy Labels via Meta Soft Label Corrector](https://mlsanity.com/paper/2008.00627/) (2020)
- [L_DMI: An Information-theoretic Noise-robust Loss Function](https://mlsanity.com/paper/1909.03388/) (2019)

## Built on by (most cited first, 30 of 33)

- [FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity](https://mlsanity.com/paper/2305.05230/) (2023)
- [Early Stopping Against Label Noise Without Validation Data](https://mlsanity.com/paper/2502.07551/) (2025)
- [Late Stopping: Avoiding Confidently Learning from Mislabeled Examples](https://mlsanity.com/paper/2308.13862/) (2023)
- [CLIPCleaner: Cleaning Noisy Labels with CLIP](https://mlsanity.com/paper/2408.10012/) (2024)
- [Fine-Grained Classification with Noisy Labels](https://mlsanity.com/paper/2303.02404/) (2023)
- [Cascade-Aware Training of Language Models](https://mlsanity.com/paper/2406.00060/) (2024)
- [CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning](https://mlsanity.com/paper/2303.10365/) (2023)
- [ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance](https://mlsanity.com/paper/2312.08852/) (2023)
- [Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations](https://mlsanity.com/paper/2305.12715/) (2023)
- [Diversified and Personalized Multi-rater Medical Image Segmentation](https://mlsanity.com/paper/2403.13417/) (2024)
- [Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection](https://mlsanity.com/paper/2405.19902/) (2024)
- [Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization](https://mlsanity.com/paper/2505.00812/) (2025)
- [FNBench: Benchmarking Robust Federated Learning against Noisy Labels](https://mlsanity.com/paper/2505.06684/) (2025)
- [MetaViewer: Towards A Unified Multi-View Representation](https://mlsanity.com/paper/2303.06329/) (2023)
- [Learning with Noisy Labels: Interconnection of Two Expectation-Maximizations](https://mlsanity.com/paper/2401.04390/) (2024)
- [Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples](https://mlsanity.com/paper/2502.08227/) (2025)
- [ChronoSelect: Robust Learning with Noisy Labels via Dynamics Temporal Memory](https://mlsanity.com/paper/2507.18183/) (2025)
- [You can't handle the (dirty) truth: Data-centric insights improve pseudo-labeling](https://mlsanity.com/paper/2406.13733/) (2024)
- [D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition](https://mlsanity.com/paper/2406.16473/) (2024)
- [LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integration](https://mlsanity.com/paper/2306.11911/) (2023)
- [Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning](https://mlsanity.com/paper/2310.15533/) (2023)
- [Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization](https://mlsanity.com/paper/2504.02996/) (2025)
- [Robust Learning of Diffusion Models with Extremely Noisy Conditions](https://mlsanity.com/paper/2510.10149/) (2025)
- [Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labels](https://mlsanity.com/paper/2401.13360/) (2024)
- [Poor-Supervised Evaluation for SuperLLM via Mutual Consistency](https://mlsanity.com/paper/2408.13738/) (2024)
- [Multi-View Oriented GPLVM: Expressiveness and Efficiency](https://mlsanity.com/paper/2502.08253/) (2025)
- [A Unified Framework for Connecting Noise Modeling to Boost Noise Detection](https://mlsanity.com/paper/2312.00827/) (2023)
- [Hypothesis Testing for Class-Conditional Noise Using Local Maximum Likelihood](https://mlsanity.com/paper/2312.10238/) (2023)
- [Jump-teaching: Combating Sample Selection Bias via Temporal Disagreement](https://mlsanity.com/paper/2405.17137/) (2024)
- [Distribution-Consistency-Guided Multi-modal Hashing](https://mlsanity.com/paper/2412.11216/) (2024)

## Abstract (arXiv)

Sample selection is an effective strategy to mitigate the effect of label noise in robust learning. Typical strategies commonly apply the small-loss criterion to identify clean samples. However, those samples lying around the decision boundary with large losses usually entangle with noisy examples, which would be discarded with this criterion, leading to the heavy degeneration of the generalization performance. In this paper, we propose a novel selection strategy, Self-Filtering (SFT), that utilizes the fluctuation of noisy examples in historical predictions to filter them, which can avoid the selection bias of the small-loss criterion for the boundary examples. Specifically, we introduce a memory bank module that stores the historical predictions of each example and dynamically updates to support the selection for the subsequent learning iteration. Besides, to reduce the accumulated error of the sample selection bias of SFT, we devise a regularization term to penalize the confident output distribution. By increasing the weight of the misclassified categories with this term, the loss function is robust to label noise in mild conditions. We conduct extensive experiments on three benchmarks with variant noise types and achieve the new state-of-the-art. Ablation studies and further analysis verify the virtue of SFT for sample selection in robust learning.