Research map / Label-efficient and robust learning / Recognition and long-tail
Quantifying and Learning Linear Symmetry-Based Disentanglement
Loek Tonnaer, Luis Armando Perez Rey, Vlado Menkovski, Mike Holenderski, Jim Portegies
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 |
|---|---|---|---|
| Use LSBD-focused methods instead of traditional disentanglement methods | Square, Arrow, Airplane, ModelNet40, and COIL-100 · Square, Arrow, Airplane, ModelNet40, and COIL-100 | D_LSBD | Improved |
| Add a limited number of transformation-labeled pairs | LSBD-VAE · Square, Arrow, and Airplane | D_LSBD | Improved |
| Train with paths of consecutive observations and known transformations | LSBD-VAE · Square, Arrow, and Airplane | D_LSBD | Improved |
| Use traditional VAE-based disentanglement methods | VAE, β-VAE, cc-VAE, FactorVAE, DIP-VAE-I/II, AdaGVAE, and AdaMLVAE · Evaluated datasets | D_LSBD | Hurt |
Closest papers by meaning
- Symmetry-induced Disentanglement on Graphs (NeurIPS 2022 · similarity 0.89)
- Theory and Evaluation Metrics for Learning Disentangled Representations (ICLR 2020 · similarity 0.89)
- Enriching Disentanglement: From Logical Definitions to Quantitative Metrics (NeurIPS 2024 · similarity 0.89)
- Commutative Lie Group VAE for Disentanglement Learning (ICML 2021 · similarity 0.88)
- Orthogonality-Enforced Latent Space in Autoencoders: An Approach to Learning Disentangled Representations (ICML 2023 · similarity 0.88)
- Disentangled Representation Learning with the Gromov-Monge Gap (ICLR 2025 · similarity 0.85)
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.
