English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  On the Role of Inductive Bias From Simulation and the Transfer to the Real World: a new Disentanglement Dataset

Gondal, M., Wuthrich, M., Miladinovic, D., Locatello, F., Breidt, M., Volchkov, V., et al. (in press). On the Role of Inductive Bias From Simulation and the Transfer to the Real World: a new Disentanglement Dataset. In Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019).

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0004-A129-8 Version Permalink: http://hdl.handle.net/21.11116/0000-0004-A12D-4
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Gondal, MW, Author
Wuthrich, M, Author
Miladinovic, D, Author
Locatello, F, Author
Breidt, M1, 2, Author              
Volchkov, V, Author
Akpo, J, Author
Bachem, O, Author
Schölkopf, B3, Author              
Bauer, S, Author
Affiliations:
1Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              
3Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Content

show
hide
Free keywords: -
 Abstract: Learning meaningful and compact representations with structurally 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 1 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.

Details

show
hide
Language(s):
 Dates: 2019-09
 Publication Status: Accepted / In Press
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019)
Place of Event: Vancouver, Canada
Start-/End Date: 2019-12-09 - 2019-12-13

Legal Case

show

Project information

show

Source 1

show
hide
Title: Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -