Unsupervised Learning of Facial Landmarks based on Inter-Intra Subject Consistencies

We present a novel unsupervised learning approach to image landmark discovery by incorporating the inter-subject landmark consistencies on facial images. This is achieved via an inter-subject mapping module that transforms original subject landmarks based on an auxiliary subject-related structure. T...

Full description

Saved in:
Bibliographic Details
Published in2020 25th International Conference on Pattern Recognition (ICPR) pp. 4077 - 4082
Main Authors Li, Weijian, Liao, Haofu, Miao, Shun, Lu, Le, Luo, Jiebo
Format Conference Proceeding
LanguageEnglish
Published IEEE 10.01.2021
Subjects
Detectors
Image synthesis
Pattern recognition
Semantics
Transforms
Unsupervised learning
Online AccessGet full text
DOI10.1109/ICPR48806.2021.9412804

Cover

More Information
Summary:We present a novel unsupervised learning approach to image landmark discovery by incorporating the inter-subject landmark consistencies on facial images. This is achieved via an inter-subject mapping module that transforms original subject landmarks based on an auxiliary subject-related structure. To recover from the transformed images back to the original subject, the landmark detector is forced to learn spatial locations that contain the consistent semantic meanings both for the paired intra-subject images and between the paired inter-subject images. Our proposed method is extensively evaluated on two public facial image datasets (MAFL, AFLW) with various settings. Experimental results indicate that our method can extract the consistent landmarks for both datasets and achieve better performances compared to the previous state-of-the-art methods quantitatively and qualitatively.
DOI:10.1109/ICPR48806.2021.9412804