Learning user's confidence for active learning

Devis Tuia*, Jordi Munoz-Mari

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

23 Citations (Scopus)

Abstract

In this paper, we study the applicability of active learning (AL) in operative scenarios. More particularly, we consider the well-known contradiction between the AL heuristics, which rank the pixels according to their uncertainty, and the user's confidence in labeling, which is related to both the homogeneity of the pixel context and user's knowledge of the scene. We propose a filtering scheme based on a classifier that learns the confidence of the user in labeling, thus minimizing the queries where the user would not be able to provide a class for the pixel. The capacity of a model to learn the user's confidence is studied in detail, also showing that the effect of resolution in such a learning task. Experiments on two QuickBird images of different resolutions (with and without pansharpening) and considering committees of users prove the efficiency of the filtering scheme proposed, which maximizes the number of useful queries with respect to traditional AL.

Original languageEnglish
Article number6247502
Pages (from-to)872-880
Number of pages9
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume51
Issue number2
DOIs
Publication statusPublished - Feb 2013
Externally publishedYes

Keywords

  • Active learning (AL)
  • bad states
  • photointerpretation
  • SVM
  • user's confidence
  • very high resolution (VHR) imagery

Fingerprint

Dive into the research topics of 'Learning user's confidence for active learning'. Together they form a unique fingerprint.

Cite this