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

20 Jan 2019  ·  Wenzhi Cao, Vahid Mirjalili, Sebastian Raschka ·

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.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Age Estimation AFAD CORAL MAE 3.48 # 1
Age Estimation CACD CORAL MAE 5.35 # 12
Age Estimation MORPH Album2 CORAL MAE 2.59 # 9
Age Estimation UTKFace CORAL MAE 5.39 # 14


No methods listed for this paper. Add relevant methods here