Browse > Computer Vision > Facial Recognition and Modelling > Unsupervised Facial Landmark Detection

Unsupervised Facial Landmark Detection

Facial landmark detection in the unsupervised setting popularized by [1]. 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.

[1] 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.

State-of-the-art leaderboards

Greatest papers with code

Unsupervised Discovery of Object Landmarks as Structural Representations

CVPR 2018 YutingZhang/lmdis-rep

Deep neural networks can model images with rich latent representations, but they cannot naturally conceptualize structures of object categories in a human-perceptible way.

UNSUPERVISED FACIAL LANDMARK DETECTION

Unsupervised Learning of Object Landmarks through Conditional Image Generation

NeurIPS 2018 tomasjakab/imm

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.

CONDITIONAL IMAGE GENERATION UNSUPERVISED FACIAL LANDMARK DETECTION

Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance

ECCV 2018 zhixinshu/DeformingAutoencoders-pytorch

In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner.

UNSUPERVISED FACIAL LANDMARK DETECTION

Self-supervised learning of a facial attribute embedding from video

21 Aug 2018oawiles/FAb-Net

We propose a self-supervised framework for learning facial attributes by simply watching videos of a human face speaking, laughing, and moving over time.

UNSUPERVISED FACIAL LANDMARK DETECTION

Unsupervised Learning of Landmarks by Descriptor Vector Exchange

18 Aug 2019jamt9000/DVE

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.

UNSUPERVISED FACIAL LANDMARK DETECTION