# How Does Heterogeneous Label Noise Impact Generalization in Neural Nets?

arXiv: https://arxiv.org/abs/2106.15475 · HTML: https://mlsanity.com/paper/2106.15475/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 29 Jun 2021.

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Probabilistic End-to-end Noise Correction for Learning with Noisy Labels](https://mlsanity.com/paper/1903.07788/) (2019)
- [Learning to Learn from Noisy Labeled Data](https://mlsanity.com/paper/1812.05214/) (2018)
- [Learning with Instance-Dependent Label Noise: A Sample Sieve Approach](https://mlsanity.com/paper/2010.02347/) (2020)
- [Learning with Feature-Dependent Label Noise: A Progressive Approach](https://mlsanity.com/paper/2103.07756/) (2021)
- [Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey](https://mlsanity.com/paper/1912.05170/) (2019)
- [Curriculum Loss: Robust Learning and Generalization against Label Corruption](https://mlsanity.com/paper/1905.10045/) (2019)
- [Augmentation Strategies for Learning with Noisy Labels](https://mlsanity.com/paper/2103.02130/) (2021)
- [Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification](https://mlsanity.com/paper/1702.05891/) (2017)
- [Deep Learning from Noisy Image Labels with Quality Embedding](https://mlsanity.com/paper/1711.00583/) (2017)
- [How does Early Stopping Help Generalization against Label Noise?](https://mlsanity.com/paper/1911.08059/) (2019)
- [Part-dependent Label Noise: Towards Instance-dependent Label Noise](https://mlsanity.com/paper/2006.07836/) (2020)
- [Contrastive Learning Improves Model Robustness Under Label Noise](https://mlsanity.com/paper/2104.08984/) (2021)
- [Improving Generalization by Controlling Label-Noise Information in Neural Network Weights](https://mlsanity.com/paper/2002.07933/) (2020)
- [Deep Learning Classification With Noisy Labels](https://mlsanity.com/paper/2004.11116/) (2020)

## Built on by (most cited first, 3 of 3)

- [Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining](https://mlsanity.com/paper/2308.04551/) (2023)
- [Algorithmic Censoring in Dynamic Learning Systems](https://mlsanity.com/paper/2305.09035/) (2023)
- [How does self-supervised pretraining improve robustness against noisy labels across various medical image classification datasets?](https://mlsanity.com/paper/2401.07990/) (2024)

## Abstract (arXiv)

Incorrectly labeled examples, or label noise, is common in real-world computer vision datasets. While the impact of label noise on learning in deep neural networks has been studied in prior work, these studies have exclusively focused on homogeneous label noise, i.e., the degree of label noise is the same across all categories. However, in the real-world, label noise is often heterogeneous, with some categories being affected to a greater extent than others. Here, we address this gap in the literature. We hypothesized that heterogeneous label noise would only affect the classes that had label noise unless there was transfer from those classes to the classes without label noise. To test this hypothesis, we designed a series of computer vision studies using MNIST, CIFAR-10, CIFAR-100, and MS-COCO where we imposed heterogeneous label noise during the training of multi-class, multi-task, and multi-label systems. Our results provide evidence in support of our hypothesis: label noise only affects the class affected by it unless there is transfer.