papers AI Learner
The Github is limit! Click to go to the new site.

Revisiting Precision and Recall Definition for Generative Model Evaluation

2019-05-14
Loïc Simon, Ryan Webster, Julien Rabin

Abstract

In this article we revisit the definition of Precision-Recall (PR) curves for generative models proposed by Sajjadi et al. (arXiv:1806.00035). Rather than providing a scalar for generative quality, PR curves distinguish mode-collapse (poor recall) and bad quality (poor precision). We first generalize their formulation to arbitrary measures, hence removing any restriction to finite support. We also expose a bridge between PR curves and type I and type II error rates of likelihood ratio classifiers on the task of discriminating between samples of the two distributions. Building upon this new perspective, we propose a novel algorithm to approximate precision-recall curves, that shares some interesting methodological properties with the hypothesis testing technique from Lopez-Paz et al (arXiv:1610.06545). We demonstrate the interest of the proposed formulation over the original approach on controlled multi-modal datasets.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.05441

PDF

https://arxiv.org/pdf/1905.05441


Similar Posts

Comments