On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset
Gondal MW, Wüthrich M, Miladinović Đ, Locatello F, Breidt M, Volchkov V, Akpo J, Bachem O, Schölkopf B, Bauer S. 2019. On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset. Advances in Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems vol. 32.
Download (ext.)
https://arxiv.org/abs/1906.03292
[Preprint]
Conference Paper
| Published
| English
Author
Gondal, Muhammad Waleed;
Wüthrich, Manuel;
Miladinović, Đorđe;
Locatello, FrancescoISTA ;
Breidt, Martin;
Volchkov, Valentin;
Akpo, Joel;
Bachem, Olivier;
Schölkopf, Bernhard;
Bauer, Stefan
Department
Abstract
Learning meaningful and compact representations with disentangled semantic
aspects is considered to be of key importance in representation learning. Since
real-world data is notoriously costly to collect, many recent state-of-the-art
disentanglement models have heavily relied on synthetic toy data-sets. In this
paper, we propose a novel data-set which consists of over one million images of
physical 3D objects with seven factors of variation, such as object color,
shape, size and position. In order to be able to control all the factors of
variation precisely, we built an experimental platform where the objects are
being moved by a robotic arm. In addition, we provide two more datasets which
consist of simulations of the experimental setup. These datasets provide for
the first time the possibility to systematically investigate how well different
disentanglement methods perform on real data in comparison to simulation, and
how simulated data can be leveraged to build better representations of the real
world. We provide a first experimental study of these questions and our results
indicate that learned models transfer poorly, but that model and hyperparameter
selection is an effective means of transferring information to the real world.
Publishing Year
Date Published
2019-06-07
Proceedings Title
Advances in Neural Information Processing Systems
Volume
32
Conference
NeurIPS: Neural Information Processing Systems
Conference Location
Vancouver, Canada
Conference Date
2019-12-08 – 2019-12-14
ISBN
IST-REx-ID
Cite this
Gondal MW, Wüthrich M, Miladinović Đ, et al. On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset. In: Advances in Neural Information Processing Systems. Vol 32. ; 2019.
Gondal, M. W., Wüthrich, M., Miladinović, Đ., Locatello, F., Breidt, M., Volchkov, V., … Bauer, S. (2019). On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset. In Advances in Neural Information Processing Systems (Vol. 32). Vancouver, Canada.
Gondal, Muhammad Waleed, Manuel Wüthrich, Đorđe Miladinović, Francesco Locatello, Martin Breidt, Valentin Volchkov, Joel Akpo, Olivier Bachem, Bernhard Schölkopf, and Stefan Bauer. “On the Transfer of Inductive Bias from Simulation to the Real World: A New Disentanglement Dataset.” In Advances in Neural Information Processing Systems, Vol. 32, 2019.
M. W. Gondal et al., “On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset,” in Advances in Neural Information Processing Systems, Vancouver, Canada, 2019, vol. 32.
Gondal MW, Wüthrich M, Miladinović Đ, Locatello F, Breidt M, Volchkov V, Akpo J, Bachem O, Schölkopf B, Bauer S. 2019. On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset. Advances in Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems vol. 32.
Gondal, Muhammad Waleed, et al. “On the Transfer of Inductive Bias from Simulation to the Real World: A New Disentanglement Dataset.” Advances in Neural Information Processing Systems, vol. 32, 2019.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Link(s) to Main File(s)
Access Level
Open Access
Export
Marked PublicationsOpen Data ISTA Research Explorer
Sources
arXiv 1906.03292