Research map / Probabilistic and scientific modeling / Variational and generative sampling
Learning Hierarchical Features from Deep Generative Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 a flat latent prior with ladder connections of increasing network depth instead of a stacked hierarchical VAE | VLAE · MNIST | feature disentanglement | Helped |
| Use a flat latent prior with ladder connections of increasing network depth instead of a stacked hierarchical VAE | VLAE · SVHN | feature disentanglement | Helped |
| Use a flat latent prior with ladder connections of increasing network depth instead of a stacked hierarchical VAE | VLAE · CelebA | feature disentanglement | Helped |
| Train a three-layer Markov HVAE with Gaussian conditionals using the ELBO | Stacked HVAE · MNIST and SVHN | hierarchical feature structure | Hurt |
Closest papers by meaning
- An Architecture for Deep, Hierarchical Generative Models (NeurIPS 2016 · similarity 0.90)
- PROGRESSIVE LEARNING AND DISENTANGLEMENT OF HIERARCHICAL REPRESENTATIONS (ICLR 2020 · similarity 0.88)
- How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model (ICML 2024 · similarity 0.87)
- Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement (ICML 2021 · similarity 0.86)
- Restyling Unsupervised Concept Based Interpretable Networks with Generative Models (ICLR 2025 · similarity 0.85)
- Learning Discrete Concepts in Latent Hierarchical Models (NeurIPS 2024 · 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.