TR2019-117

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


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 framework 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-theart 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.

 

  • Software Download

  • Related News & Events

    •  AWARD   MERL Researchers win Best Paper Award at ICCV 2019 Workshop on Statistical Deep Learning in Computer Vision
      Date: October 27, 2019
      Awarded to: Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Chen Feng, Xiaoming Liu
      MERL Contact: Tim Marks
      Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
      Brief
      • MERL researcher Tim Marks, former MERL interns Abhinav Kumar and Wenxuan Mou, and MERL consultants Professor Chen Feng (NYU) and Professor Xiaoming Liu (MSU) received the Best Oral Paper Award at the IEEE/CVF International Conference on Computer Vision (ICCV) 2019 Workshop on Statistical Deep Learning in Computer Vision (SDL-CV) held in Seoul, Korea. Their paper, entitled "UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss," describes a method which, given an image of a face, estimates not only the locations of facial landmarks but also the uncertainty of each landmark location estimate.
    •