Self-Paced Deep Regression Forests with Consideration on Underrepresented Examples
This work addresses bias in computer vision models for applications such as facial analysis, though it is incremental as it builds on existing self-paced learning and deep regression forest methods.
The paper tackles the problem of bias in deep discriminative models for tasks like facial age and head pose estimation by proposing self-paced deep regression forests that incorporate fairness to address underrepresented examples, achieving state-of-the-art performance on these tasks.
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.