AI Paper Atlas

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

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Prediction-powered and conformal inference · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use TopP&R instead of P&R or D&C for evaluation with outliersGenerative-model evaluation · 64-dimensional Gaussian shift with outliersfidelity and diversity trend accuracyImproved
Use TopP&R instead of P&R or D&C for simultaneous mode-drop evaluationGenerative-model evaluation · Seven-mode Gaussian mixturesrecallImproved
Use TopP&R instead of P&R or D&C under Non-IID perturbationsGenerative-model evaluation · Gaussian scatter and swap noisescore stability: 15%Improved
Use TopP&R instead of MTD to measure increasing image distortionImage distortion evaluation · FFHQ noisy image featuresdistortion sensitivityImproved
Use TopP&R rather than P&R, D&C, or MTD across embedding modelsCIFAR-10 generative-model ranking · CIFAR-10, varying embeddersmean Hamming Distance: 1.33 vs 2.66, 3.0, and 3.33Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy