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...
Những tác giả chính: | Thewlis, J, Albanie, S, Bilen, H, Vedaldi, A |
---|---|
Định dạng: | Conference item |
Ngôn ngữ: | English |
Được phát hành: |
IEEE
2020
|
Những quyển sách tương tự
-
Unsupervised learning of object landmarks by factorized spatial embeddings
Bằng: Thewlis, J, et al.
Được phát hành: (2017) -
Modelling and unsupervised learning of symmetric deformable object categories
Bằng: Thewlis, J, et al.
Được phát hành: (2018) -
Unsupervised learning of object frames by dense equivariant image labelling
Bằng: Thewlis, J, et al.
Được phát hành: (2017) -
Unsupervised learning of object landmarks through conditional image generation
Bằng: Jakab, T, et al.
Được phát hành: (2018) -
Learning grimaces by watching TV
Bằng: Albanie, S, et al.
Được phát hành: (2016)