Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection

03/26/2019
by   Zhiwei Liu, et al.
4

Recently, deep learning based facial landmark detection has achieved great success. Despite this, we notice that the semantic ambiguity greatly degrades the detection performance. Specifically, the semantic ambiguity means that some landmarks (e.g. those evenly distributed along the face contour) do not have clear and accurate definition, causing inconsistent annotations by annotators. Accordingly, these inconsistent annotations, which are usually provided by public databases, commonly work as the ground-truth to supervise network training, leading to the degraded accuracy. To our knowledge, little research has investigated this problem. In this paper, we propose a novel probabilistic model which introduces a latent variable, i.e. the 'real' ground-truth which is semantically consistent, to optimize. This framework couples two parts (1) training landmark detection CNN and (2) searching the 'real' ground-truth. These two parts are alternatively optimized: the searched 'real' ground-truth supervises the CNN training; and the trained CNN assists the searching of 'real' ground-truth. In addition, to recover the unconfidently predicted landmarks due to occlusion and low quality, we propose a global heatmap correction unit (GHCU) to correct outliers by considering the global face shape as a constraint. Extensive experiments on both image-based (300W and AFLW) and video-based (300-VW) databases demonstrate that our method effectively improves the landmark detection accuracy and achieves the state of the art performance.

READ FULL TEXT

page 1

page 3

page 5

research
04/08/2021

Generative Landmarks

We propose a general purpose approach to detect landmarks with improved ...
research
06/05/2023

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

Recently, deep learning-based facial landmark detection has achieved sig...
research
12/09/2020

Robust Facial Landmark Detection by Multi-order Multi-constraint Deep Networks

Recently, heatmap regression has been widely explored in facial landmark...
research
07/18/2017

Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses

Facial alignment involves finding a set of landmark points on an image w...
research
05/26/2023

Contouring by Unit Vector Field Regression

This work introduces a simple deep-learning based method to delineate co...
research
04/20/2020

Utilizing Mask R-CNN for Waterline Detection in Canoe Sprint Video Analysis

Determining a waterline in images recorded in canoe sprint training is a...
research
05/28/2018

Deep Adversarial Context-Aware Landmark Detection for Ultrasound Imaging

Real-time localization of prostate gland in trans-rectal ultrasound imag...

Please sign up or login with your details

Forgot password? Click here to reset