Convolutional Ordinal Regression Forest for Image Ordinal Estimation

TL;DR

This paper introduces CORF, a novel convolutional ordinal regression forest that jointly learns ordinal relationships and binary classifiers end-to-end, improving accuracy and stability in image ordinal estimation tasks.

Contribution

The paper proposes CORF, integrating ordinal regression with differentiable decision trees and CNNs for simultaneous learning of ordinal distributions, unlike previous methods.

Findings

Significant improvements in facial age estimation accuracy.

Enhanced stability over existing ordinal regression methods.

Effective in image aesthetic assessment tasks.

Abstract

Image ordinal estimation is to predict the ordinal label of a given image, which can be categorized as an ordinal regression problem. Recent methods formulate an ordinal regression problem as a series of binary classification problems. Such methods cannot ensure that the global ordinal relationship is preserved since the relationships among different binary classifiers are neglected. We propose a novel ordinal regression approach, termed Convolutional Ordinal Regression Forest or CORF, for image ordinal estimation, which can integrate ordinal regression and differentiable decision trees with a convolutional neural network for obtaining precise and stable global ordinal relationships. The advantages of the proposed CORF are twofold. First, instead of learning a series of binary classifiers \emph{independently}, the proposed method aims at learning an ordinal distribution for ordinal regression by optimizing those binary classifiers \emph{simultaneously}. Second, the differentiable decision trees in the proposed CORF can be trained together with the ordinal distribution in an end-to-end manner. The effectiveness of the proposed CORF is verified on two image ordinal estimation tasks, i.e. facial age estimation and image aesthetic assessment, showing significant improvements and better stability over the state-of-the-art ordinal regression methods.