Self-Paced Deep Regression Forests with Consideration on Underrepresented Samples

Deep discriminative models (e.g. deep regression forests, deep Gaussian process) have been extensively studied recently to solve problems such as facial age estimation and head pose estimation. Most existing methods pursue to achieve robust and unbiased solutions through either learning more discriminative features, or weighting samples. We argue what is more desirable is to gradually learn to discriminate like our human being, and hence we resort to self-paced learning (SPL). Then, a natural question arises: can self-paced regime guide deep discriminative models to obtain more robust and less unbiased solutions? To this end, this paper proposes a new deep discriminative model--self-paced deep regression forests considering sample uncertainty (SPUDRFs). It builds up a new self-paced learning paradigm: easy and underrepresented samples first. This paradigm could be extended to combine with a variety of deep discriminative models. 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.

Self-Paced Deep Regression Forests for Facial Age Estimation

Facial age estimation is an important and challenging problem in computer vision. Existing approaches usually employ deep neural networks to fit the mapping from facial features to age directly, even though there exist some noisy and confusing samples. We argue that it is more desirable to distinguish noisy and confusing facial images from regular ones, and suppress the interference arising from them. To this end, we propose self-paced deep regression forests (SP-DRFs) -- a gradual learning DNNs framework for age estimation. As the model is learned gradually, from easy to hard, it tends to be significantly more robust with emphasizing more on reliable samples and avoiding bad local minima. We demonstrate the efficacy of SP-DRFs on Morph II and FG-NET datasets, where our method is shown to achieve state-of-the-art performance.