Disentangling Visual Priors: Unsupervised Learning of Scene Interpretations with Compositional Autoencoder
[ 1 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ 2 ] Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ P ] pracownik | [ SzD ] doktorant ze Szkoły Doktorskiej
2024
rozdział w monografii naukowej / referat
angielski
- scene representation
- image understanding
- disentanglement
EN Contemporary deep learning architectures lack principled means for capturing and handling fundamental visual concepts, like objects, shapes, geometric transforms, and other higher-level structures. We propose a neurosymbolic architecture that uses a domain-specific language to capture selected priors of image formation, including object shape, appearance, categorization, and geometric transforms. We express template programs in that language and learn their parameterization with features extracted from the scene by a convolutional neural network. When executed, the parameterized program produces geometric primitives which are rendered and assessed for correspondence with the scene content and trained via auto-association with gradient. We confront our approach with a baseline method on a synthetic benchmark and demonstrate its capacity to disentangle selected aspects of the image formation process, learn from small data, correct inference in the presence of noise, and out-of-sample generalization.
10.09.2024
240 - 256
20