Weakly supervised learning of foreground-background segmentation using masked RBMs

Authors:
Nicolas Heess;Nicolas Le Roux;John Winn
Affiliations:
University of Edinburgh, IANC, Edinburgh, UK;INRIA, Paris, France;Microsoft Research, Cambridge, UK
Venue:
ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
Year:
2011

Citing 7
Cited 1

Training products of experts by minimizing contrastive divergence

Neural Computation
Greedy learning of multiple objects in images using robust statistics and factorial learning

Neural Computation
A fast learning algorithm for deep belief nets

Neural Computation
Training restricted Boltzmann machines using approximations to the likelihood gradient

Proceedings of the 25th international conference on Machine learning
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Similarity scores based on background samples

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Learning a generative model of images by factoring appearance and shape

Neural Computation

The Shape Boltzmann Machine: A Strong Model of Object Shape

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

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.