# Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets

arXiv: https://arxiv.org/abs/2207.01573 · HTML: https://mlsanity.com/paper/2207.01573/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 52 references that are in the map.
- First posted on arXiv 4 Jul 2022.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (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)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Training Deep Neural Networks on Noisy Labels with Bootstrapping](https://mlsanity.com/paper/1412.6596/) (2014)
- [Exploring the Limits of Out-of-Distribution Detection](https://mlsanity.com/paper/2106.03004/) (2021)
- [WebVision Database: Visual Learning and Understanding from Web Data](https://mlsanity.com/paper/1708.02862/) (2017)
- [Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy](https://mlsanity.com/paper/1908.04951/) (2019)
- [Iterative Learning with Open-set Noisy Labels](https://mlsanity.com/paper/1804.00092/) (2018)
- [Multi-Objective Interpolation Training for Robustness to Label Noise](https://mlsanity.com/paper/2012.04462/) (2020)
- [Jo-SRC: A Contrastive Approach for Combating Noisy Labels](https://mlsanity.com/paper/2103.13029/) (2021)
- [Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2108.05617/) (2021)
- [Faster Meta Update Strategy for Noise-Robust Deep Learning](https://mlsanity.com/paper/2104.15092/) (2021)
- [Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach](https://mlsanity.com/paper/2108.02399/) (2021)
- [EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels](https://mlsanity.com/paper/2011.05704/) (2020)

## Built on by (most cited first, 6 of 6)

- [Is your noise correction noisy? PLS: Robustness to label noise with two stage detection](https://mlsanity.com/paper/2210.04578/) (2022)
- [Manifold DivideMix: A Semi-Supervised Contrastive Learning Framework for Severe Label Noise](https://mlsanity.com/paper/2308.06861/) (2023)
- [Cluster-aware Contrastive Learning for Unsupervised Out-of-distribution Detection](https://mlsanity.com/paper/2302.02598/) (2023)
- [PLOOD: Partial Label Learning with Out-of-distribution Objects](https://mlsanity.com/paper/2403.06681/) (2024)
- [An accurate detection is not all you need to combat label noise in web-noisy datasets](https://mlsanity.com/paper/2407.05528/) (2024)
- [Self-Ensemble Post Learning for Noisy Domain Generalization](https://mlsanity.com/paper/2512.10818/) (2025)

## Abstract (arXiv)

Using search engines for web image retrieval is a tempting alternative to manual curation when creating an image dataset, but their main drawback remains the proportion of incorrect (noisy) samples retrieved. These noisy samples have been evidenced by previous works to be a mixture of in-distribution (ID) samples, assigned to the incorrect category but presenting similar visual semantics to other classes in the dataset, and out-of-distribution (OOD) images, which share no semantic correlation with any category from the dataset. The latter are, in practice, the dominant type of noisy images retrieved. To tackle this noise duality, we propose a two stage algorithm starting with a detection step where we use unsupervised contrastive feature learning to represent images in a feature space. We find that the alignment and uniformity principles of contrastive learning allow OOD samples to be linearly separated from ID samples on the unit hypersphere. We then spectrally embed the unsupervised representations using a fixed neighborhood size and apply an outlier sensitive clustering at the class level to detect the clean and OOD clusters as well as ID noisy outliers. We finally train a noise robust neural network that corrects ID noise to the correct category and utilizes OOD samples in a guided contrastive objective, clustering them to improve low-level features. Our algorithm improves the state-of-the-art results on synthetic noise image datasets as well as real-world web-crawled data. Our work is fully reproducible github.com/PaulAlbert31/SNCF.