A Learnable Spectral Memory Graph for Recognition and Segmentation
Penn collection
General Robotics, Automation, Sensing and Perception Laboratory
Degree type
Discipline
Subject
segmentation
recognition
learning spectral graph
derivative of eigenvectors
normalized cuts
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Contributor
Abstract
Image segmentation is often treated as an unsupervised task. Segmentation by human, in contrast, relies heavily on memory to produce an object-like clustering, through a mechanism of controlled hallucination. This paper presents a learning algorithm for memory-driven object segmentation and recognition. We propose a general spectral graph learning algorithm based on gradient descent in the space of graph weight matrix using derivatives of eigenvectors. The gradients are efficiently computed using the theory of implicit functions. This algorithm effectively learns a graph network capable of memorizing and retrieving multiple patterns given noisy inputs. We demonstrate the validity of this approach on segmentation and recognition tasks, including geometric shape extraction, and hand-written digit recognition.
Advisor
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Publication date
Volume number
Issue number
Publisher
Publisher DOI
Comments
University of Pennsylvania Department of Computer and Information Science Technical Report No. MS-CIS-04-12.