AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset

Muhammad Waleed Gondal, Manuel Wuthrich, Djordje Miladinovic, Francesco Locatello, Martin Breidt, Valentin Volchkov, Joel Akpo, Olivier Bachem, Bernhard Schölkopf, Stefan Bauer

NeurIPS 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 58 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
transfer learned representations directly from simulation to real data instead of training on real datadisentanglement VAEs · MPI3D-realMIGHurt
transfer model and hyperparameter choice selected on realistic simulation to real datadisentanglement VAEs · MPI3D-realprobability of beating random model: 72% vs 50% chanceImproved
transfer model and hyperparameter choice selected on simple toy simulation to real datadisentanglement VAEs · MPI3D-realprobability of beating random model: 78% vs 50% chanceImproved
use toy simulation instead of realistic simulation as source for hyperparameter transferdisentanglement VAEs · MPI3D-realprobability of beating random model: 72 -> 78Mixed
use real data instead of simulated data for reconstructiondisentanglement VAEs · reconstruction scorereconstruction scoreHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy