Research map / Adversarial robustness and security / Attacks on text and graphs
Non-Adversarial Mapping with VAEs
Yedid Hoshen
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 |
|---|---|---|---|
| replace per-example latent codes (NAM) with a learned stochastic VAE encoder | NAM · MNIST->SVHN | translated digit accuracy (%): 31.9 -> 51.7 | Improved |
| replace deterministic encoder (AE-NAM) with stochastic VAE encoder (ablation) | VAE-NAM · MNIST->SVHN | translated digit accuracy (%): 16.7 -> 51.7 | Improved |
| replace deterministic encoder (AE-NAM) with stochastic VAE encoder (ablation) | VAE-NAM · SVHN->MNIST | translated digit accuracy (%): 37.4 -> 37.4 | No clear effect |
| replace per-example latent codes (NAM) with VAE encoder | NAM · SVHN->MNIST | translated digit accuracy (%): 33.3 -> 37.4 | Improved |
| replace per-example latent codes (NAM) with VAE encoder | NAM · Car2Car | root median residual error: 1.47 -> 1.38 | Improved |
| replace optimization-based inference (NAM) with feedforward encoder | NAM · Evaluating 100 analogies, 64x64 | evaluation time: 23s -> 0.013s | Improved |
| use stochastic VAE encoder instead of deterministic AE-NAM (ablation) | VAE-NAM · edges2shoes | realism and sample variety (qualitative) | Mixed |
Closest papers by meaning
- NAM: Non-Adversarial Unsupervised Domain Mapping (ECCV 2018 · similarity 0.88)
- Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs (JMLR 2021 · similarity 0.88)
- Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping (CVPR 2019 · similarity 0.85)
- Estimating the Success of Unsupervised Image to Image Translation (ECCV 2018 · similarity 0.84)
- DiffAdvMAP: Flexible Diffusion-Based Framework for Generating Natural Unrestricted Adversarial Examples (ICML 2025 · similarity 0.83)
- Toward Improving Robustness and Accuracy in Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.82)
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.
