Facial landmark detection in the unsupervised setting popularized by . The evaluation occurs in two stages: (1) Embeddings are first learned in an unsupervised manner (i.e. without labels); (2) A simple regressor is trained to regress landmarks from the unsupervised embedding.
 Thewlis, James, Hakan Bilen, and Andrea Vedaldi. "Unsupervised learning of object landmarks by factorized spatial embeddings." Proceedings of the IEEE International Conference on Computer Vision. 2017.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Deep neural networks can model images with rich latent representations, but they cannot naturally conceptualize structures of object categories in a human-perceptible way.
#2 best model for Unsupervised Facial Landmark Detection on AFLW (Zhang CVPR 2018 crops)
We propose a method for learning landmark detectors for visual objects (such as the eyes and the nose in a face) without any manual supervision.
In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner.
#4 best model for Unsupervised Facial Landmark Detection on MAFL
We propose a self-supervised framework for learning facial attributes by simply watching videos of a human face speaking, laughing, and moving over time.
#2 best model for Unsupervised Facial Landmark Detection on 300W
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.