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...
主要な著者: | Thewlis, J, Albanie, S, Bilen, H, Vedaldi, A |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
IEEE
2020
|
類似資料
-
Unsupervised learning of object landmarks by factorized spatial embeddings
著者:: Thewlis, J, 等
出版事項: (2017) -
Modelling and unsupervised learning of symmetric deformable object categories
著者:: Thewlis, J, 等
出版事項: (2018) -
Unsupervised learning of object frames by dense equivariant image labelling
著者:: Thewlis, J, 等
出版事項: (2017) -
Unsupervised learning of object landmarks through conditional image generation
著者:: Jakab, T, 等
出版事項: (2018) -
Learning grimaces by watching TV
著者:: Albanie, S, 等
出版事項: (2016)