Timezone: »

 
Poster
On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset
Muhammad Waleed Gondal · Manuel Wuethrich · Djordje Miladinovic · Francesco Locatello · Martin Breidt · Valentin Volchkov · Joel Akpo · Olivier Bachem · Bernhard Schölkopf · Stefan Bauer

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #35
in Algorithms -- Representation Learning »

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 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.

Keywords: Representation Learning · Data Sets or Data Repositories · Algorithms · Data, Challenges, Implementations, and Software
[ Paper]  [ Poster] 

Author Information

Muhammad Waleed Gondal (Max Planck Institute for Intelligent Systems)
Manuel Wuethrich (Max Planck Institute for Intelligent Systems)
Djordje Miladinovic (ETH Zurich)
Francesco Locatello (ETH Zürich - MPI Tübingen)
Martin Breidt (MPI for Biological Cybernetics)
Valentin Volchkov (Max Planck Institut for Intelligent Systems)
Joel Akpo (Max Planck Institute for Intelligent Systems)
Olivier Bachem (Google Brain)
Bernhard Schölkopf (MPI for Intelligent Systems)

Bernhard Scholkopf received degrees in mathematics (London) and physics (Tubingen), and a doctorate in computer science from the Technical University Berlin. He has researched at AT&T Bell Labs, at GMD FIRST, Berlin, at the Australian National University, Canberra, and at Microsoft Research Cambridge (UK). In 2001, he was appointed scientific member of the Max Planck Society and director at the MPI for Biological Cybernetics; in 2010 he founded the Max Planck Institute for Intelligent Systems. For further information, see www.kyb.tuebingen.mpg.de/~bs.

Stefan Bauer (MPI for Intelligent Systems)

More from the Same Authors