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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| transfer learned representations directly from simulation to real data instead of training on real data | disentanglement VAEs · MPI3D-real | MIG | Hurt |
| transfer model and hyperparameter choice selected on realistic simulation to real data | disentanglement VAEs · MPI3D-real | probability of beating random model: 72% vs 50% chance | Improved |
| transfer model and hyperparameter choice selected on simple toy simulation to real data | disentanglement VAEs · MPI3D-real | probability of beating random model: 78% vs 50% chance | Improved |
| use toy simulation instead of realistic simulation as source for hyperparameter transfer | disentanglement VAEs · MPI3D-real | probability of beating random model: 72 -> 78 | Mixed |
| use real data instead of simulated data for reconstruction | disentanglement VAEs · reconstruction score | reconstruction score | Hurt |
Closest papers by meaning
- On the Transfer of Disentangled Representations in Realistic Settings (ICLR 2021 · similarity 0.92)
- Transferring disentangled representations: bridging the gap between synthetic and real images (NeurIPS 2024 · similarity 0.90)
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations (ICML 2019 · similarity 0.89)
- Disentangled Representation Learning via Modular Compositional Bias (NeurIPS 2025 · similarity 0.88)
- Disentangled Representation Learning in Non-Markovian Causal Systems (NeurIPS 2024 · similarity 0.87)
- Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning (ICML 2024 · similarity 0.87)
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.
