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...
Main Authors: | Thewlis, J, Albanie, S, Bilen, H, Vedaldi, A |
---|---|
格式: | Conference item |
语言: | English |
出版: |
IEEE
2020
|
相似书籍
-
Unsupervised learning of object landmarks by factorized spatial embeddings
由: Thewlis, J, et al.
出版: (2017) -
Modelling and unsupervised learning of symmetric deformable object categories
由: Thewlis, J, et al.
出版: (2018) -
Unsupervised learning of object frames by dense equivariant image labelling
由: Thewlis, J, et al.
出版: (2017) -
Unsupervised learning of object landmarks through conditional image generation
由: Jakab, T, et al.
出版: (2018) -
Learning grimaces by watching TV
由: Albanie, S, et al.
出版: (2016)