Experiments on two real-world data sets produce accuracy estimates within a few percent of the true accuracy, using solely unlabeled data. Our models also ...

May 19, 2017 · We propose an efficient method to estimate the accuracy of classifiers using only unlabeled data. We consider a setting with multiple classification problems.

This paper presents an unsupervised approach for estimating accuracies, meaning that only unlabeled data are required. Being able to estimate the accuracies of ...

We consider the question of how unlabeled data can be used to estimate the true accuracy of learned classifiers, and the related question of how outputs ...

A simple graphical model is presented that performs well in practice, and two nonparametric extensions to it that improve its performance are provided that ...

We first show how to estimate error rates exactly from unlabeled data when given a collection of competing classifiers that make independent errors, based on ...

We propose an efficient method to estimate the accuracy of classifiers using only unlabeled data. We consider a setting with multiple classification ...

We propose an efficient method to estimate the accuracy of classifiers using only unlabeled data. We consider a setting with multiple classification problems ...

An efficient method to estimate the accuracy of classifiers using only unlabeled data is proposed, based on the intuition that when classifiers agree, ...

Paper ID: 691 Title: Estimating Accuracy from Unlabeled Data: A Bayesian Approach Review #1 ===== Summary of the paper (Summarize the main claims ...