UGLLI face alignment: Estimating uncertainty with gaussian log-likelihood loss

Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Chen Feng, Xiaoming Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages778-782
Number of pages5
ISBN (Electronic)9781728150239
DOIs
StatePublished - Oct 2019
Event17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of
Duration: Oct 27 2019Oct 28 2019

Publication series

NameProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Conference

Conference17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
CountryKorea, Republic of
CitySeoul
Period10/27/1910/28/19

Keywords

  • Face alignment
  • Gaussian log likelihood loss
  • Uncertainty estimation

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'UGLLI face alignment: Estimating uncertainty with gaussian log-likelihood loss'. Together they form a unique fingerprint.

Cite this