# KNN-enhanced Deep Learning Against Noisy Labels

arXiv: https://arxiv.org/abs/2012.04224 · HTML: https://mlsanity.com/paper/2012.04224/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 4 of 4)

- [Detecting Corrupted Labels Without Training a Model to Predict](https://mlsanity.com/paper/2110.06283/) (2021)
- [An Embedding is Worth a Thousand Noisy Labels](https://mlsanity.com/paper/2408.14358/) (2024)
- [Noise-Aware Framework for Correcting Corrupted Labels](https://mlsanity.com/paper/2606.11695/) (2026)
- [A Multi-Branch Hierarchy-Aware Framework for Heterogeneous Audio Classification](https://mlsanity.com/paper/2607.01974/) (2026)

## Abstract (arXiv)

Supervised learning on Deep Neural Networks (DNNs) is data hungry. Optimizing performance of DNN in the presence of noisy labels has become of paramount importance since collecting a large dataset will usually bring in noisy labels. Inspired by the robustness of K-Nearest Neighbors (KNN) against data noise, in this work, we propose to apply deep KNN for label cleanup. Our approach leverages DNNs for feature extraction and KNN for ground-truth label inference. We iteratively train the neural network and update labels to simultaneously proceed towards higher label recovery rate and better classification performance. Experiment results show that under the same setting, our approach outperforms existing label correction methods and achieves better accuracy on multiple datasets, e.g.,76.78% on Clothing1M dataset.