Unsupervised learning of landmarks by descriptor vector exchange
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...
Autori principali: | Thewlis, J, Albanie, S, Bilen, H, Vedaldi, A |
---|---|
Natura: | Conference item |
Lingua: | English |
Pubblicazione: |
IEEE
2020
|
Documenti analoghi
-
Unsupervised learning of object landmarks by factorized spatial embeddings
di: Thewlis, J, et al.
Pubblicazione: (2017) -
Modelling and unsupervised learning of symmetric deformable object categories
di: Thewlis, J, et al.
Pubblicazione: (2018) -
Unsupervised learning of object frames by dense equivariant image labelling
di: Thewlis, J, et al.
Pubblicazione: (2017) -
Unsupervised learning of object landmarks through conditional image generation
di: Jakab, T, et al.
Pubblicazione: (2018) -
Learning grimaces by watching TV
di: Albanie, S, et al.
Pubblicazione: (2016)