UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss

Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Chen Feng, Xiaoming Liu; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0

Abstract


Modern face alignment methods have become quite accurate at predicting the locations of facial landmarks, but they do not typically estimate the uncertainty of their predicted locations. In this paper, we present a novel frame-work for jointly predicting facial landmark locations and the associated uncertainties, modeled as 2D Gaussian distributions, using Gaussian log-likelihood loss. Not only does our joint estimation of uncertainty and landmark locations yield state-of-the-art estimates of the uncertainty of predicted landmark locations, but it also yields state-of-the-art estimates for the landmark locations (face alignment). Our method's estimates of the uncertainty of landmarks' predicted locations could be used to automatically identify input images on which face alignment fails, which can be critical for downstream tasks.

Related Material


[pdf]
[bibtex]
@InProceedings{Kumar_2019_ICCV,
author = {Kumar, Abhinav and Marks, Tim K. and Mou, Wenxuan and Feng, Chen and Liu, Xiaoming},
title = {UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2019}
}