Research map / Probabilistic and scientific modeling / Variational and generative sampling
Unsupervised Representation Learning From Sparse Transformation Analysis
Yue Song, T. Anderson Keller, Yisong Yue, Pietro Perona, Max Welling
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 STA unsupervised instead of unsupervised VAE baselines | FactorVAE · MNIST | scaling equivariance error: 659.71 -> 281.32 | Improved |
| use STA instead of supervised LatentFlow | LatentFlow · MNIST | average log-likelihood: -2112.45 -> -2107.65 | Improved |
| use STA instead of supervised LatentFlow | LatentFlow · MNIST | rotation equivariance error: 153.54 -> 230.93 | Hurt |
| use STA instead of supervised PoFlow | PoFlow · MNIST | rotation equivariance error: 231.42 -> 230.93 | No clear effect |
| use STA instead of supervised LatentFlow | LatentFlow · Shapes3D | average log-likelihood: -11215.42 -> -11199.93 | Improved |
| use STA instead of supervised LatentFlow | LatentFlow · Shapes3D | floor hue equivariance error: 613.29 -> 1005.23 | Hurt |
| use STA instead of supervised PoFlow | PoFlow · Shapes3D | object hue equivariance error: 912.48 -> 928.10 | No clear effect |
| use STA instead of supervised LatentFlow on composite transformations | LatentFlow · MNIST (composite) | scaling + rotation equivariance error: 493.75 -> 293.45 | Improved |
| use STA instead of supervised LatentFlow on composite transformations | LatentFlow · MNIST (composite) | rotation + coloring equivariance error: 452.63 -> 407.95 | Improved |
| use STA instead of supervised LatentFlow | LatentFlow · Falcor3D | lighting intensity equivariance error: 5798.42 -> 8672.91 | Hurt |
| use STA instead of supervised PoFlow | PoFlow · Isaac3D | object scale equivariance error: 6188.59 -> 6104.74 | No clear effect |
| use STA instead of supervised LatentFlow | LatentFlow · Isaac3D | robot X-move equivariance error: 3659.72 -> 7012.34 | Hurt |
Closest papers by meaning
- From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit (NeurIPS 2025 · similarity 0.87)
- Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning (ICLR 2025 · similarity 0.87)
- Neural Fourier Transform: A General Approach to Equivariant Representation Learning (ICLR 2024 · similarity 0.86)
- Sequential Disentanglement by Extracting Static Information From A Single Sequence Element (ICML 2024 · similarity 0.86)
- Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation (ICML 2025 · similarity 0.86)
- From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication (ICLR 2024 · similarity 0.86)
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.
