Computing Precision and Recall with Missing or Uncertain Ground Truth - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Book Sections Year : 2013

Computing Precision and Recall with Missing or Uncertain Ground Truth

Abstract

In this paper we present a way to use precision and recall measures in total absence of ground truth. We develop a probabilistic interpretation of both measures and show that, provided a sufficient number of data sources are available, it offers a viable performance measure to compare methods if no ground truth is available. This paper also shows the limitations of the approach, in case a systematic bias is present in all compared methods, but shows that it maintains a very high level of overall coherence and stability. It opens broader perspectives and can be extended to handling partial or unreliable ground truth, as well as levels of prior confidence in the methods it aims to compare.
Fichier principal
Vignette du fichier
GREC_2011_LNCS.pdf (413.11 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-00778188 , version 1 (18-01-2013)

Identifiers

Cite

Bart Lamiroy, Tao Sun. Computing Precision and Recall with Missing or Uncertain Ground Truth. Young-Bin Kwon and Jean-Marc Ogier. Graphics Recognition. New Trends and Challenges. 9th International Workshop, GREC 2011, Seoul, Korea, September 15-16, 2011, Revised Selected Papers, 7423, Springer, pp.149-162, 2013, Lecture Notes in Computer Science, 978-3-642-36823-3. ⟨10.1007/978-3-642-36824-0_15⟩. ⟨hal-00778188⟩
272 View
1936 Download

Altmetric

Share

Gmail Facebook X LinkedIn More