# Noisy Labels for Weakly Supervised Gamma Hadron Classification

arXiv: https://arxiv.org/abs/2108.13396 · HTML: https://mlsanity.com/paper/2108.13396/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 40 references that are in the map.
- First posted on arXiv 30 Aug 2021.

## Builds on (most cited first, 10 of 10)

- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning](https://mlsanity.com/paper/1609.06570/) (2016)
- [Classification with Asymmetric Label Noise: Consistency and Maximal Denoising](https://mlsanity.com/paper/1303.1208/) (2013)
- [Making Risk Minimization Tolerant to Label Noise](https://mlsanity.com/paper/1403.3610/) (2014)
- [Classification without labels: Learning from mixed samples in high energy physics](https://mlsanity.com/paper/1708.02949/) (2017)
- [(Machine) Learning to Do More with Less](https://mlsanity.com/paper/1706.09451/) (2017)

## Abstract (arXiv)

Gamma hadron classification, a central machine learning task in gamma ray astronomy, is conventionally tackled with supervised learning. However, the supervised approach requires annotated training data to be produced in sophisticated and costly simulations. We propose to instead solve gamma hadron classification with a noisy label approach that only uses unlabeled data recorded by the real telescope. To this end, we employ the significance of detection as a learning criterion which addresses this form of weak supervision. We show that models which are based on the significance of detection deliver state-of-the-art results, despite being exclusively trained with noisy labels; put differently, our models do not require the costly simulated ground-truth labels that astronomers otherwise employ for classifier training. Our weakly supervised models exhibit competitive performances also on imbalanced data sets that stem from a variety of other application domains. In contrast to existing work on class-conditional label noise, we assume that only one of the class-wise noise rates is known.