Self-Paced Deep Regression Forests with Consideration on Underrepresented Examples

TL;DR

This paper introduces SPUDRFs, a self-paced deep regression forest model that improves robustness and fairness by focusing on underrepresented examples, achieving state-of-the-art results in facial age and head pose estimation.

Contribution

It proposes a novel self-paced learning framework for deep regression forests that emphasizes fairness towards underrepresented data points, enhancing model robustness.

Findings

Achieves state-of-the-art performance on facial age estimation.

Demonstrates robustness and fairness improvements over existing methods.

Validates effectiveness on head pose estimation.

Abstract

Deep discriminative models (e.g. deep regression forests, deep neural decision forests) have achieved remarkable success recently to solve problems such as facial age estimation and head pose estimation. Most existing methods pursue robust and unbiased solutions either through learning discriminative features, or reweighting samples. We argue what is more desirable is learning gradually to discriminate like our human beings, and hence we resort to self-paced learning (SPL). Then, a natural question arises: can self-paced regime lead deep discriminative models to achieve more robust and less biased solutions? To this end, this paper proposes a new deep discriminative model--self-paced deep regression forests with consideration on underrepresented examples (SPUDRFs). It tackles the fundamental ranking and selecting problem in SPL from a new perspective: fairness. This paradigm is fundamental and could be easily combined with a variety of deep discriminative models (DDMs). Extensive experiments on two computer vision tasks, i.e., facial age estimation and head pose estimation, demonstrate the efficacy of SPUDRFs, where state-of-the-art performances are achieved.