Unsupervised Learning of Landmarks by Descriptor Vector Exchange

18 Aug 2019James ThewlisSamuel AlbanieHakan BilenAndrea Vedaldi

Equivariance to random image transformations is an effective method to learn landmarks of object categories, such as the eyes and the nose in faces, without manual supervision. However, this method does not explicitly guarantee that the learned landmarks are consistent with changes between different instances of the same object, such as different facial identities... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Unsupervised Facial Landmark Detection 300W DVE NME 4.65 # 1
Unsupervised Facial Landmark Detection AFLW-MTFL DVE NME 7.53 # 1
Unsupervised Facial Landmark Detection AFLW (Zhang CVPR 2018 crops) DVE NME 6.54 # 2
Unsupervised Facial Landmark Detection MAFL DVE NME 2.86 # 2