Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Tomographic Auto-Encoder: Unsupervised Bayesian Recovery of Corrupted Data
Francesco Tonolini, Pablo Garcia Moreno, Andreas Damianou, Roderick Murray-Smith
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 TAE instead of MIWAE | MNIST recovery · MNIST, 50% missing | ELBO: 917 ± 4 -> 1719 ± 7 | Improved |
| Use TAE instead of MIWAE | MNIST recovery · MNIST, 80% missing | ELBO: 780 ± 6 -> 1536 ± 14 | Improved |
| Use TAE instead of MIWAE | Fashion-MNIST recovery · Fashion-MNIST, 50% missing | ELBO: 800 ± 7 -> 1326 ± 7 | Improved |
| Use TAE instead of MIWAE | Fashion-MNIST recovery · Fashion-MNIST, 80% missing | ELBO: 766 ± 8 -> 1094 ± 13 | Improved |
| Use TAE instead of MIWAE | UCI HAR recovery · UCI HAR, 50% missing | ELBO: 613 ± 6 -> 1014 ± 6 | Improved |
| Use TAE instead of MIWAE | UCI HAR recovery · UCI HAR, 80% missing | ELBO: 584 ± 8 -> 854 ± 52 | Improved |
| Use TAE instead of MVAE | MNIST recovery with structured missing values · MNIST, structured missing (10 × 10 window) | ELBO: 428 -> 638 | Improved |
| Use TAE imputations rather than raw corrupted data or MVAE imputations | Downstream classification · MNIST and Fashion-MNIST | classification accuracy | Improved |
| Vary reduced-entropy hyperparameters C and λ across a broad range (ablation) | TAE · MNIST, 90% missing values with additive noise | ELBO | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MIWAE — MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets (ICML 2019) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learn From Unpaired Data for Image Restoration: A Variational Bayes Approach (TPAMI 2022 · similarity 0.87)
- Provable Posterior Sampling with Denoising Oracles via Tilted Transport (NeurIPS 2024 · similarity 0.86)
- Diffusion Priors for Variational Likelihood Estimation and Image Denoising (NeurIPS 2024 · similarity 0.85)
- How many measurements are enough? Bayesian recovery in inverse problems with general distributions (NeurIPS 2025 · similarity 0.85)
- Sparse Variational Student-t Processes (AAAI 2024 · similarity 0.85)
- Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models (ICML 2024 · similarity 0.84)
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.
