Sciweavers

Share
CORR
2011
Springer

Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs

7 years 9 months ago
Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs
Abstract. We propose an extension of the Restricted Boltzmann Machine (RBM) that allows the joint shape and appearance of foreground objects in cluttered images to be modeled independently of the background. We present a learning scheme that learns this representation directly from cluttered images with only very weak supervision. The model generates plausible samples and performs foreground-background segmentation. We demonstrate that representing foreground objects independently of the background can be beneficial in recognition tasks.
Nicolas Heess, Nicolas Le Roux, John M. Winn
Added 20 Aug 2011
Updated 20 Aug 2011
Type Journal
Year 2011
Where CORR
Authors Nicolas Heess, Nicolas Le Roux, John M. Winn
Comments (0)
books