# Detection and Mitigation of Rare Subclasses in Deep Neural Network Classifiers

arXiv: https://arxiv.org/abs/1911.12780 · HTML: https://mlsanity.com/paper/1911.12780/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2019.

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

- [Discrete-Event Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components](https://mlsanity.com/paper/2202.03360/) (2022)
- [Keep your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring](https://mlsanity.com/paper/2207.05078/) (2022)
- [Scope Compliance Uncertainty Estimate](https://mlsanity.com/paper/2312.10801/) (2023)
- [A New Framework to Analyse the Distributional Robustness of Deep Neural Networks](https://mlsanity.com/paper/2605.21313/) (2026)

## Abstract (arXiv)

Regions of high-dimensional input spaces that are underrepresented in training datasets reduce machine-learnt classifier performance, and may lead to corner cases and unwanted bias for classifiers used in decision making systems. When these regions belong to otherwise well-represented classes, their presence and negative impact are very hard to identify. We propose an approach for the detection and mitigation of such rare subclasses in deep neural network classifiers. The new approach is underpinned by an easy-to-compute commonality metric that supports the detection of rare subclasses, and comprises methods for reducing the impact of these subclasses during both model training and model exploitation. We demonstrate our approach using two well-known datasets, MNIST's handwritten digits and Kaggle's cats/dogs, identifying rare subclasses and producing models which compensate for subclass rarity. In addition we demonstrate how our run-time approach increases the ability of users to identify samples likely to be misclassified at run-time.