# Improving the classification of extreme classes by means of loss regularisation and generalised beta distributions

arXiv: https://arxiv.org/abs/2407.12417 · HTML: https://mlsanity.com/paper/2407.12417/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 53 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [A Deep Learning Interpretable Classifier for Diabetic Retinopathy Disease Grading](https://mlsanity.com/paper/1712.08107/) (2017)
- [TLU-Net: A Deep Learning Approach for Automatic Steel Surface Defect Detection](https://mlsanity.com/paper/2101.06915/) (2021)
- [An ordinal CNN approach for the assessment of neurological damage in Parkinson's disease patients](https://mlsanity.com/paper/2106.05230/) (2021)
- [Validation of artificial neural networks to model the acoustic behaviour of induction motors](https://mlsanity.com/paper/2401.15377/) (2024)

## Abstract (arXiv)

An ordinal classification problem is one in which the target variable takes values on an ordinal scale. Nowadays, there are many of these problems associated with real-world tasks where it is crucial to accurately classify the extreme classes of the ordinal structure. In this work, we propose a unimodal regularisation approach that can be applied to any loss function to improve the classification performance of the first and last classes while maintaining good performance for the remainder. The proposed methodology is tested on six datasets with different numbers of classes, and compared with other unimodal regularisation methods in the literature. In addition, performance in the extreme classes is compared using a new metric that takes into account their sensitivities. Experimental results and statistical analysis show that the proposed methodology obtains a superior average performance considering different metrics. The results for the proposed metric show that the generalised beta distribution generally improves classification performance in the extreme classes. At the same time, the other five nominal and ordinal metrics considered show that the overall performance is aligned with the performance of previous alternatives.