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

By Wenzhi Cao, Vahid Mirjalili, Sebastian Raschka. Pattern Recognition Letters, 2019

370 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/072229ccbdbac7289b6067167a0279ae38a269f9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Rinon Gal
  2. Daniel Cohen-Or
  3. Yotam Nitzan
  4. Ofir Brenner

In Computer Vision and Pattern Recognition

  1. Rinon Gal
  2. Daniel Cohen-Or
  3. Yotam Nitzan
  4. Ofir Brenner
  5. Eli Shechtman
  6. Yuval Alaluf
  7. Alexei A. Efros
  8. Or Patashnik

Citations in the corpus