Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs

Details Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs

2011-07-19

arxiv.org/abs/1107.3823v1

International Conference on Artificial Neural Networks (2011)

Computer Science

Learning

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-515355