Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression

2021/03/25 by Wanhua Li, Xiaoke Huang, Li, Wanhua +7 · 11 citations
Computer Science · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning and Data Classification #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.2103.13629

Accepted by CVPR2021. Code is available at https://github.com/Li-Wanhua/POEs

arxiv created 2021/03/25 · openalex publication_date 2021/03/25 · arxiv updated 2021/03/26 · openalex created_date 2021/03/29 · openalex updated_date 2026/07/28

Abstract

Uncertainty is the only certainty there is. Modeling data uncertainty is essential for regression, especially in unconstrained settings. Traditionally the direct regression formulation is considered and the uncertainty is modeled by modifying the output space to a certain family of probabilistic distributions. On the other hand, classification based regression and ranking based solutions are more popular in practice while the direct regression methods suffer from the limited performance. How to model the uncertainty within the present-day technologies for regression remains an open issue. In this paper, we propose to learn probabilistic ordinal embeddings which represent each data as a multivariate Gaussian distribution rather than a deterministic point in the latent space. An ordinal distribution constraint is proposed to exploit the ordinal nature of regression. Our probabilistic ordinal embeddings can be integrated into popular regression approaches and empower them with the ability of uncertainty estimation. Experimental results show that our approach achieves competitive performance. Code is available at https://github.com/Li-Wanhua/POEs.

Citations

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Auto-Encoding Variational Bayes
• A NEW MEASURE OF RANK CORRELATION
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates

Cited by

• D3O: Dynamic Distribution Distillation for Ordinal Regression
• Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models
• IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
• Parameterized Diffusion Optimization enabled Autoregressive Ordinal Regression for Diabetic Retinopathy Grading
• STORM: Benchmarking Visual Rating of MLLMs with a Comprehensive Ordinal Regression Dataset
• Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression
• Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer
• DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Features
• FaceInsight: A Multimodal Large Language Model for Face Perception
• CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Loss
• OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM

Related

• Approximately Unimodal Likelihood Models for Ordinal Regression
• Uncertainty Quantification for Regression using Proper Scoring Rules
• Aleatoric and Epistemic Uncertainty Measures for Ordinal Classification through Binary Reduction
• Ordinal Regression as Structured Classification
• Semi-Supervised Ordinal Regression Based on Empirical Risk Minimization