paper-with-me

Papers

Unimodal probability distributions for deep ordinal classification

2017-05-15 · ICML 2017 8 · Christopher Beckham, Christopher Pal

Probability distributions produced by the cross-entropy loss for ordinal classification problems can possess undesired properties. We propose a straightforward technique to constrain discrete ordinal probability distributions to be unimodal via the use of the Poisson and binomial probability distributions. We evaluate this approach in the context of deep learning on two large ordinal image datasets, obtaining promising results.

📄 PDF Abstract BibTeX arXiv:1705.05278

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationOrdinal Classification

Similar Papers 제목 키워드 기반

Approximately Unimodal Likelihood Models for Ordinal Regression

2025-09-30 · Ryoya Yamasaki arxiv

Ordinal regression (OR, also called ordinal classification) is classification of ordinal data, in which the underlying target variable is categorical and considered to have a natural ordinal relation for the underlying e…

Ordinal Classification

Unimodal Distributions for Ordinal Regression

2023-03-08 · Jaime S. Cardoso, Ricardo Cruz, Tomé Albuquerque

In many real-world prediction tasks, class labels contain information about the relative order between labels that are not captured by commonly used loss functions such as multicategory cross-entropy. Recently, the prefe…

regression

Ordinal Semantic Segmentation Applied to Medical and Odontological Images

2026-03-21 · Mariana Dória Prata Lima, Gilson Antonio Giraldi, Jaime S. Cardoso arxiv

Semantic segmentation consists of assigning a semantic label to each pixel according to predefined classes. This process facilitates the understanding of object appearance and spatial relationships, playing an important …

Ordinal ClassificationSemantic Segmentation

Quasi-Unimodal Distributions for Ordinal Classification

2022-03-18 · Mathematics 2022 3 · Tomé Albuquerque, Ricardo Cruz, Jaime S. Cardoso

Ordinal classification tasks are present in a large number of different domains. However, common losses for deep neural networks, such as cross-entropy, do not properly weight the relative ordering between classes. For t…

ClassificationOrdinal Classification

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

2024-07-17 · Víctor Manuel Vargas, Pedro Antonio Gutiérrez, Javier Barbero-Gómez, César Hervás-Martínez

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 classi…

Ordinal Classification