Research map / Label-efficient and robust learning / Recognition and long-tail
NestedVAE: Isolating Common Factors via Weak Supervision
Check 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 NestedVAE instead of infoVAE | Rotated MNIST representations · Rotated MNIST, 0° transfer domain | digit-classification F1: 0.629±0.141 -> 0.708±0.211 | Helped |
| Use NestedVAE instead of DIP-VAE-I | Rotated MNIST representations · Rotated MNIST, 0° transfer domain | rotation-classification F1: 0.511±0.012 -> 0.373±0.029 | Helped |
| Use NestedVAE instead of infoVAE | Rotated MNIST representations · Rotated MNIST | adjusted parity: 0.603 -> 0.664 | Helped |
| Use NestedVAE instead of Rare-Event VAE | Rotated MNIST change detection · Rotated MNIST change detection | accuracy: 0.7166 -> 0.7380 | Helped |
| Use NestedVAE instead of β-VAE | UTKFace sex prediction across race · UTKFace, female sex prediction across race | adjusted parity: 0.410 -> 0.641 | Helped |
| Use NestedVAE instead of DIPVAE-I | UTKFace sex prediction across race · UTKFace, male sex prediction across race | adjusted parity: 0.547 -> 0.699 | Helped |
Closest papers by meaning
- beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework (ICLR 2017 · similarity 0.88)
- CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation (NeurIPS 2026 · similarity 0.86)
- Local Causal Structure Learning in the Presence of Latent Variables (ICML 2024 · similarity 0.85)
- $\alpha$TC-VAE: On the relationship between Disentanglement and Diversity (ICLR 2024 · similarity 0.85)
- Nested Learning: The Illusion of Deep Learning Architectures (NeurIPS 2025 · similarity 0.84)
- A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data (ICLR 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.