Rank consistent ordinal regression for neural networks with application to age estimation

Abstract

In many real-world prediction tasks, class labels include information about the relative ordering between labels, which is not captured by commonly-used loss functions such as multi-category cross-entropy. Recently, the deep learning community adopted ordinal regression frameworks to take such ordering information into account. Neural networks were equipped with ordinal regression capabilities by transforming ordinal targets into binary classification subtasks. However, this method suffers from inconsistencies among the different binary classifiers. To resolve these inconsistencies, we propose the COnsistent RAnk Logits (CORAL) framework with strong theoretical guarantees for rank-monotonicity and consistent confidence scores. Moreover, the proposed method is architecture-agnostic and can extend arbitrary state-of-the-art deep neural network classifiers for ordinal regression tasks. The empirical evaluation of the proposed rank-consistent method on a range of face-image datasets for age prediction shows a substantial reduction of the prediction error compared to the reference ordinal regression network.

arXiv commentupdated to published version

References in corpus (1)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library

Cited by in corpus (15)

• Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition
• Deep Neural Networks for Rank-Consistent Ordinal Regression Based On Conditional Probabilities
• Improving Face-Based Age Estimation with Attention-Based Dynamic Patch Fusion
• Class Distance Weighted Cross Entropy Loss for Classification of Disease Severity
• Integrating ConvNeXt and Vision Transformers for Enhancing Facial Age Estimation
• Gait-based Age Group Classification with Adaptive Graph Neural Network
• Extreme Cardiac MRI Analysis under Respiratory Motion: Results of the CMRxMotion Challenge
• Overcoming Occlusions in the Wild: A Multi-Task Age Head Approach to Age Estimation
• A Neural Approach to Ordinal Regression for the Preventive Assessment of Developmental Dyslexia
• Machine learning for smell: Ordinal odor strength prediction of molecular perfumery components
• Deep Ordinal Regression using Optimal Transport Loss and Unimodal Output Probabilities
• Hierarchical Attention-based Age Estimation and Bias Estimation
• LM-PCVMNet: Pediatric Cervical Vertebral Maturation Analysis with Deep Fusion of Landmarks and Metadata
• Prediction of clinical tremor severity using Rank Consistent Ordinal Regression
• Pairwise Fairness for Ordinal Regression