NIPS2009_0039_slide - Occlusive Components Analysis Jrg...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
References Numerical Experiments Application to images of cluttered objects. A Selection of 14 of the N = 500 data points. B Changes of the parameters W and T for the algorithm with H = 8 hidden units. Each row shows W and T for the specified EM iteration. C Feature vectors at different iterations stages displayed as point in color space. Black circles are the current model values and grey circles those of the previous iterations. Combining Masks and Features A Illustration of how two object masks and features combine to generate an image (without noise). B Graphical model of the generation process with hidden permutation variable . The Generative Model Abstract We study unsupervised learning in a probabilistic generative model for occlusion. The problem of occlusion is addressed from the perspective of multiple-causes models such as NMF [1], sparse coding [2], or ICA. The model features - binary hidden variables encoding object presence
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/12/2010 for the course COMPUTER S 10586 taught by Professor Jilinwang during the Fall '09 term at Zhejiang University.

Ask a homework question - tutors are online