Learning viewpoint planning in active recognition on a small sampling budget: a Kriging approach - CentraleSupélec Access content directly
Conference Papers Year : 2010

Learning viewpoint planning in active recognition on a small sampling budget: a Kriging approach

Abstract

This paper focuses on viewpoint planning for 3D active object recognition. The objective is to design a planning policy into a Q-learning framework with a limited number of samples. Most existing stochastic techniques are therefore inapplicable. We propose to use Kriging and Bayesian Optimization coupled with Q-learning to obtain a computationally-efficient viewpoint-planning design, under a restrictive sampling budget. Experimental results on a representative database, including a comparison with classical approaches, show promising results for this strategy.
Fichier principal
Vignette du fichier
DTIM1041.1291040181.pdf (1.57 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00520814 , version 1 (08-09-2011)

Identifiers

  • HAL Id : hal-00520814 , version 1

Cite

Joseph Defretin, Julien Marzat, Hélène Piet-Lahanier. Learning viewpoint planning in active recognition on a small sampling budget: a Kriging approach. 9th IEEE Conference on Machine Learning and Applications, ICMLA 2010, Dec 2010, Washington, D.C., United States. pp.169-174. ⟨hal-00520814⟩
256 View
302 Download

Share

Gmail Mastodon Facebook X LinkedIn More