Research map / Probabilistic and scientific modeling / Molecules and proteins
TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models
Pum Jun Kim, Yoojin Jang, Jisu Kim, Jaejun Yoo
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 TopP&R instead of P&R or D&C for evaluation with outliers | Generative-model evaluation · 64-dimensional Gaussian shift with outliers | fidelity and diversity trend accuracy | Improved |
| Use TopP&R instead of P&R or D&C for simultaneous mode-drop evaluation | Generative-model evaluation · Seven-mode Gaussian mixtures | recall | Improved |
| Use TopP&R instead of P&R or D&C under Non-IID perturbations | Generative-model evaluation · Gaussian scatter and swap noise | score stability: 15% | Improved |
| Use TopP&R instead of MTD to measure increasing image distortion | Image distortion evaluation · FFHQ noisy image features | distortion sensitivity | Improved |
| Use TopP&R rather than P&R, D&C, or MTD across embedding models | CIFAR-10 generative-model ranking · CIFAR-10, varying embedders | mean Hamming Distance: 1.33 vs 2.66, 3.0, and 3.33 | Improved |
Closest papers by meaning
- A Unifying Information-theoretic Perspective on Evaluating Generative Models (AAAI 2025 · similarity 0.88)
- Position: All Current Generative Fidelity and Diversity Metrics are Flawed (ICML 2025 · similarity 0.88)
- Efficient Precision and Recall Metrics for Assessing Generative Models using Hubness-aware Sampling (ICML 2024 · similarity 0.88)
- When and how can inexact generative models still sample from the data manifold? (NeurIPS 2025 · similarity 0.87)
- PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation (ICLR 2025 · similarity 0.86)
- Sampling is as easy as keeping the consistency: convergence guarantee for Consistency Models (ICML 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.
