# Label Noise Types and Their Effects on Deep Learning

arXiv: https://arxiv.org/abs/2003.10471 · HTML: https://mlsanity.com/paper/2003.10471/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 29 of 29)

- [Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond](https://mlsanity.com/paper/2104.01493/) (2021)
- [Detecting Label Errors by using Pre-Trained Language Models](https://mlsanity.com/paper/2205.12702/) (2022)
- [AQuA: A Benchmarking Tool for Label Quality Assessment](https://mlsanity.com/paper/2306.09467/) (2023)
- [Generalized Data Weighting via Class-level Gradient Manipulation](https://mlsanity.com/paper/2111.00056/) (2021)
- [On the Robustness of Monte Carlo Dropout Trained with Noisy Labels](https://mlsanity.com/paper/2103.12002/) (2021)
- [Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLM-Powered Assistance](https://mlsanity.com/paper/2504.02901/) (2025)
- [SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training](https://mlsanity.com/paper/2210.04525/) (2022)
- [RoS-KD: A Robust Stochastic Knowledge Distillation Approach for Noisy Medical Imaging](https://mlsanity.com/paper/2210.08388/) (2022)
- [Handling Realistic Label Noise in BERT Text Classification](https://mlsanity.com/paper/2305.16337/) (2023)
- [Differences Between Hard and Noisy-labeled Samples: An Empirical Study](https://mlsanity.com/paper/2307.10718/) (2023)
- [Ambiguous Annotations: When is a Pedestrian not a Pedestrian?](https://mlsanity.com/paper/2405.08794/) (2024)
- [Improving Label Error Detection and Elimination with Uncertainty Quantification](https://mlsanity.com/paper/2405.09602/) (2024)
- [Improved Stochastic Optimization of LogSumExp](https://mlsanity.com/paper/2509.24894/) (2025)
- [The Influence of Faulty Labels in Data Sets on Human Pose Estimation](https://mlsanity.com/paper/2409.03887/) (2024)
- [AlleNoise: large-scale text classification benchmark dataset with real-world label noise](https://mlsanity.com/paper/2407.10992/) (2024)
- [Uncertainty estimation via ensembles of deep learning models and dropout layers for seismic traces](https://mlsanity.com/paper/2410.06120/) (2024)
- [Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification](https://mlsanity.com/paper/2503.16873/) (2025)
- [Combining Self-labeling with Selective Sampling](https://mlsanity.com/paper/2301.04420/) (2023)
- [Human-annotated label noise and their impact on ConvNets for remote sensing image scene classification](https://mlsanity.com/paper/2305.12106/) (2023)
- [TopoMortar: A dataset to evaluate image segmentation methods focused on topology accuracy](https://mlsanity.com/paper/2503.03365/) (2025)
- [Evaluating Facial Expression Recognition Datasets for Deep Learning: A Benchmark Study with Novel Similarity Metrics](https://mlsanity.com/paper/2503.20428/) (2025)
- [Generation and Analysis of Feature-Dependent Pseudo Noise for Training Deep Neural Networks](https://mlsanity.com/paper/2105.10796/) (2021)
- [Deep Metric Learning with Locality Sensitive Angular Loss for Self-Correcting Source Separation of Neural Spiking Signals](https://mlsanity.com/paper/2110.07046/) (2021)
- [Deep Learning with Label Noise: A Hierarchical Approach](https://mlsanity.com/paper/2205.14299/) (2022)
- [Establishment of Neural Networks Robust to Label Noise](https://mlsanity.com/paper/2211.15279/) (2022)
- [When the Small-Loss Trick is Not Enough: Multi-Label Image Classification with Noisy Labels Applied to CCTV Sewer Inspections](https://mlsanity.com/paper/2410.07689/) (2024)
- [Bayesian uncertainty-aware deep learning with noisy labels: Tackling annotation ambiguity in EEG seizure detection](https://mlsanity.com/paper/2410.19815/) (2024)
- [Robust Testing for Deep Learning using Human Label Noise](https://mlsanity.com/paper/2412.00244/) (2024)
- [Table2Image: Lightweight Tabular Learning with Generated Proxy Representations and Reliability Diagnostics](https://mlsanity.com/paper/2412.06265/) (2024)

## Abstract (arXiv)

The recent success of deep learning is mostly due to the availability of big datasets with clean annotations. However, gathering a cleanly annotated dataset is not always feasible due to practical challenges. As a result, label noise is a common problem in datasets, and numerous methods to train deep neural networks in the presence of noisy labels are proposed in the literature. These methods commonly use benchmark datasets with synthetic label noise on the training set. However, there are multiple types of label noise, and each of them has its own characteristic impact on learning. Since each work generates a different kind of label noise, it is problematic to test and compare those algorithms in the literature fairly. In this work, we provide a detailed analysis of the effects of different kinds of label noise on learning. Moreover, we propose a generic framework to generate feature-dependent label noise, which we show to be the most challenging case for learning. Our proposed method aims to emphasize similarities among data instances by sparsely distributing them in the feature domain. By this approach, samples that are more likely to be mislabeled are detected from their softmax probabilities, and their labels are flipped to the corresponding class. The proposed method can be applied to any clean dataset to synthesize feature-dependent noisy labels. For the ease of other researchers to test their algorithms with noisy labels, we share corrupted labels for the most commonly used benchmark datasets. Our code and generated noisy synthetic labels are available online.