Self-supervised learning of structural representations of visual objects
This thesis explores how a computer can learn the structure of visual objects in the absence of strong supervision using self-supervised learning. We demonstrate that we can learn structural representations of objects using an autoencoding framework with reconstruction as the key learning signal. We...
| Auteur principal: | |
|---|---|
| Autres auteurs: | |
| Format: | Thèse |
| Langue: | English |
| Publié: |
2021
|
| Sujets: |