AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Learning Interpretable Low-dimensional Representation via Physical Symmetry

Xuanjie Liu, Daniel Chin, Yichen Huang, Gus Xia

NeurIPS 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 0 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
Add latent-space physical symmetry augmentation (K=4) (ablation)SPS_VAE for monophonic music · Monophonic music test setSynthesis R²: 0.910$\pm$0.040 -> \textbf{0.986$\pm$0.025}Improved
Add latent-space physical symmetry augmentation (K=4) (ablation)SPS_AE for monophonic music · Monophonic music test setSynthesis R²: 0.832$\pm$0.129 -> \textbf{0.986$\pm$0.025}Improved
Add latent-space physical symmetry augmentation (K=4) (ablation)SPS_VAE for bouncing-ball videos · Bouncing ball test setLocation linear-fit MSE: 0.62 $\pm$ 0.14 -> 0.26 $\pm$ 0.30Improved
Add latent-space physical symmetry augmentation (K=4) (ablation)SPS_AE for bouncing-ball videos · Bouncing ball test setLocation linear-fit MSE: 0.42 $\pm$ 0.15 -> \textbf{0.24 $\pm$ 0.17}Improved
Use an AE instead of a VAESPS for monophonic music · Monophonic music test setSynthesis R²: 0.986$\pm$0.025 -> \textbf{0.986$\pm$0.025}No clear effect
Use an AE instead of a VAESPS for bouncing-ball videos · Bouncing ball test setLocation linear-fit MSE: 0.26 $\pm$ 0.30 -> \textbf{0.24 $\pm$ 0.17}No clear effect
Replace SPS with reconstruction-only β-VAEMonophonic music representation learning · Monophonic music test setLearned factor R²: 0.999$\pm$0.001 -> 0.772$\pm$0.333Hurt
Remove the separate style representation (ablation)SPS_VAE+ for multiple-instrument audio · Multiple-instrument audio test setTimbre augmentation precision: 0.98 -> 0.50Hurt
Remove the separate style representation (ablation)SPS_VAE+ for colourful bouncing-ball videos · Colourful bouncing ball test setColour augmentation precision: 0.99 -> 0.64Hurt
Increase the counterfactual augmentation factor KSPS for bouncing-ball videos · Bouncing ball training sets of 256, 512, 1024, and 2048 samplesLinear projection lossImproved
Use perturbed, deliberately incorrect symmetry groups instead of no symmetrySPS for bouncing-ball videos · Bouncing ball datasetLinear projection lossImproved
Add symmetry constraints to the sequential autoencoder (ablation)SPS for audio · Monophonic music test setPrior prediction loss: 0.0030$\pm$0.0033 -> 0.0012$\pm$0.0006Improved

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