Learning Spectral Graph Segmentation
Document Type Conference Paper
©2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
We present a general graph learning algo- rithm for spectral graph partitioning, that allows direct supervised learning of graph structures using hand labeled training exam- ples. The learning algorithm is based on gradient descent in the space of all feasible graph weights. Computation of the gradient involves finding the derivatives of eigenvec- tors with respect to the graph weight matrix. We show the derivatives of eigenvectors exist and can be computed in an exact analytical form using the theory of implicit functions. Furthermore, we show for a simple case, the gradient converges exponentially fast. In the image segmentation domain, we demonstrate how to encode top-down high level object prior in a bottom-up shape detection process.
Date Posted: 17 July 2012