SOTAVerified

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.

( Image credit: Unsupervised learning of object landmarks by factorized spatial embeddings )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–15 of 15 papers

TitleStatusHype
Unsupervised Image Representation Learning with Deep Latent ParticlesCode1
AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking KeypointsCode1
GANSeg: Learning to Segment by Unsupervised Hierarchical Image GenerationCode1
Unsupervised Part-Based Disentangling of Object Shape and AppearanceCode1
Self-supervised learning of a facial attribute embedding from videoCode1
Unsupervised Part Segmentation through Disentangling Appearance and Shape—0
LatentKeypointGAN: Controlling Images via Latent KeypointsCode0
Unsupervised Learning of Landmarks by Descriptor Vector ExchangeCode0
SCOPS: Self-Supervised Co-Part SegmentationCode0
Deep Feature Factorization For Concept DiscoveryCode0
Unsupervised Learning of Object Landmarks through Conditional Image GenerationCode0
Deforming Autoencoders: Unsupervised Disentangling of Shape and AppearanceCode0
Unsupervised Discovery of Object Landmarks as Structural RepresentationsCode0
Unsupervised learning of object frames by dense equivariant image labelling—0
Unsupervised learning of object landmarks by factorized spatial embeddingsCode0
Show:102550

No leaderboard results yet.