PROPEL: Probabilistic Parametric Regression Loss for Convolutional Neural Networks

1 code implementation • 28 Jul 2018 • Muhammad Asad, Rilwan Basaru, S M Masudur Rahman Al Arif, Greg Slabaugh

We propose a PRObabilistic Parametric rEgression Loss (PROPEL) that facilitates CNNs to learn parameters of probability distributions for addressing probabilistic regression problems.

Head Pose Estimation regression