Conference item icon

Conference item : Poster

Reconstruction bottlenecks in object-centric generative models

Abstract:
A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision. However, these are largely restricted to visually simple images; robust object discovery in real-world sensory datasets remains elusive. To increase the understanding of such inductive biases, we empirically investigate the role of “reconstruction bottlenecks” for scene decomposition in GENESIS, a recent VAE-based model. We show such bottlenecks determine reconstruction and segmentation quality and critically influence model behaviour.
Publication status:
Published
Peer review status:
Reviewed (other)

Actions

Access Document

Publication website:
https://oolworkshop.github.io/program/ool_5.html

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Pembroke College
Role:
Author


Publisher:
International Conference on Machine Learning
Publication date:
2020-07-17
Acceptance date:
2020-06-01
Event title:
Workshop on Object-Oriented Learning at ICML 2020
Event series:
International Conference on Machine Learning
Event location:
Online
Event website:
https://icml.cc/Conferences/2020
Event start date:
2020-07-12
Event end date:
2020-07-18


Language:
English
Keywords:
Subtype:
Poster
Pubs id:
1138269
Local pid:
pubs:1138269
Deposit date:
2020-10-19
ARK identifier:

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP