# Deep k-NN for Noisy Labels

arXiv: https://arxiv.org/abs/2004.12289 · HTML: https://mlsanity.com/paper/2004.12289/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2020.

## Built on by (most cited first, 30 of 55)

- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [Deep Learning Through the Lens of Example Difficulty](https://mlsanity.com/paper/2106.09647/) (2021)
- [FINE Samples for Learning with Noisy Labels](https://mlsanity.com/paper/2102.11628/) (2021)
- [Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels](https://mlsanity.com/paper/2102.05291/) (2021)
- [Detecting Corrupted Labels Without Training a Model to Predict](https://mlsanity.com/paper/2110.06283/) (2021)
- [Learning with Neighbor Consistency for Noisy Labels](https://mlsanity.com/paper/2202.02200/) (2022)
- [Identifiability of Label Noise Transition Matrix](https://mlsanity.com/paper/2202.02016/) (2022)
- [From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model](https://mlsanity.com/paper/2205.00690/) (2022)
- [Neighborhood Collective Estimation for Noisy Label Identification and Correction](https://mlsanity.com/paper/2208.03207/) (2022)
- [Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection](https://mlsanity.com/paper/2111.14932/) (2021)
- [CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels](https://mlsanity.com/paper/2312.06221/) (2023)
- [AQuA: A Benchmarking Tool for Label Quality Assessment](https://mlsanity.com/paper/2306.09467/) (2023)
- [CLIPCleaner: Cleaning Noisy Labels with CLIP](https://mlsanity.com/paper/2408.10012/) (2024)
- [Machine Learning with Confidential Computing: A Systematization of Knowledge](https://mlsanity.com/paper/2208.10134/) (2022)
- [Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images](https://mlsanity.com/paper/2109.10778/) (2021)
- [SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise](https://mlsanity.com/paper/2111.11288/) (2021)
- [DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling](https://mlsanity.com/paper/2305.19395/) (2023)
- [BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification](https://mlsanity.com/paper/2203.01937/) (2022)
- [VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models](https://mlsanity.com/paper/2309.16211/) (2023)
- [Locally Adaptive Label Smoothing for Predictive Churn](https://mlsanity.com/paper/2102.05140/) (2021)
- [Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels](https://mlsanity.com/paper/2210.08826/) (2022)
- [LEMoN: Label Error Detection using Multimodal Neighbors](https://mlsanity.com/paper/2407.18941/) (2024)
- [Integrating kNN with Foundation Models for Adaptable and Privacy-Aware Image Classification](https://mlsanity.com/paper/2402.12500/) (2024)
- [An Embedding is Worth a Thousand Noisy Labels](https://mlsanity.com/paper/2408.14358/) (2024)
- [ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense](https://mlsanity.com/paper/2106.14300/) (2021)
- [Learning with Noisy Labels through Learnable Weighting and Centroid Similarity](https://mlsanity.com/paper/2303.09470/) (2023)
- [Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning](https://mlsanity.com/paper/2403.02690/) (2024)
- [Multi-Branch Deep Radial Basis Function Networks for Facial Emotion Recognition](https://mlsanity.com/paper/2109.03336/) (2021)
- [CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypes](https://mlsanity.com/paper/2310.09761/) (2023)
- [Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection](https://mlsanity.com/paper/2102.05131/) (2021)

## Abstract (arXiv)

Modern machine learning models are often trained on examples with noisy labels that hurt performance and are hard to identify. In this paper, we provide an empirical study showing that a simple k-nearest neighbor-based filtering approach on the logit layer of a preliminary model can remove mislabeled training data and produce more accurate models than many recently proposed methods. We also provide new statistical guarantees into its efficacy.