Learning Natural Image Structure with a Horizontal Product Model

Urs Köster, Jussi T. Lindgren, Michael Gutmann, Aapo Hyvärinen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a novel extension to Independent Component Analysis (ICA), where the data is generated as the product of two submodels, each of which follow an ICA model, and which combine in a horizontal fashion. This is in contrast to previous nonlinear extensions to ICA which were based on a hierarchy of layers. We apply the product model to natural image patches and report the emergence of localized masks in the additional network layer, while the Gabor features that are obtained in the primary layer change their tuning properties and become less localized. As an interpretation we suggest that the model learns to separate the localization of image features from other properties, since identity and position of a feature are plausibly independent. We also show that the horizontal model can be interpreted as an overcomplete model where the features are no longer independent.
Original languageEnglish
Title of host publicationIndependent Component Analysis and Signal Separation
Subtitle of host publication8th International Conference, ICA 2009, Paraty, Brazil, March 15-18, 2009. Proceedings
EditorsTülay Adali, Christian Jutten, João Marcos Travassos Romano, Allan Kardec Barros
Place of PublicationBerlin, Heidelberg
PublisherSpringer Berlin Heidelberg
Pages507-514
Number of pages8
ISBN (Electronic)978-3-642-00599-2
ISBN (Print)978-3-642-00598-5
DOIs
Publication statusPublished - 2009

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume5441
ISSN (Print)0302-9743

Fingerprint Dive into the research topics of 'Learning Natural Image Structure with a Horizontal Product Model'. Together they form a unique fingerprint.

Cite this