Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Chapter

Download BibTeX

Title

Disentangling Visual Priors: Unsupervised Learning of Scene Interpretations with Compositional Autoencoder

Authors

[ 1 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ 2 ] Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ P ] employee | [ SzD ] doctoral school student

Scientific discipline (Law 2.0)

[2.3] Information and communication technology

Year of publication

2024

Chapter type

chapter in monograph / paper

Publication language

english

Keywords
EN
  • scene representation
  • image understanding
  • disentanglement
Abstract

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.

Date of online publication

10.09.2024

Pages (from - to)

240 - 256

DOI

10.1007/978-3-031-71167-1_13

URL

https://link.springer.com/chapter/10.1007/978-3-031-71167-1_13

Book

Neural-Symbolic Learning and Reasoning : 18th International Conference, NeSy 2024, Barcelona, Spain, September 9–12, 2024, Proceedings, Part I

Presented on

18th International Conference on Neural-Symbolic Learning and Reasoning NeSy 2024, 9-12.09.2024, Barcelona, Spain

Ministry points / chapter

20

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.