Unsupervised learning of object landmarks by factorized spatial embeddings
Learning automatically the structure of object categories remains an important open problem in computer vision. In this paper, we propose a novel unsupervised approach that can discover and learn landmarks in object categories, thus characterizing their structure. Our approach is based on factorizin...
Autors principals: | Thewlis, J, Bilen, H, Vedaldi, A |
---|---|
Format: | Conference item |
Publicat: |
IEEE
2017
|
Ítems similars
-
Unsupervised learning of landmarks by descriptor vector exchange
per: Thewlis, J, et al.
Publicat: (2020) -
Modelling and unsupervised learning of symmetric deformable object categories
per: Thewlis, J, et al.
Publicat: (2018) -
Unsupervised learning of object frames by dense equivariant image labelling
per: Thewlis, J, et al.
Publicat: (2017) -
Unsupervised learning of object landmarks through conditional image generation
per: Jakab, T, et al.
Publicat: (2018) -
Unsupervised learning of probably symmetric deformable 3D objects from images in the wild
per: Wu, S, et al.
Publicat: (2021)