Hierarchical Modeling of Local Image Features through Lp-Nested Symmetric 
Distributions

Sinz, F; Simoncelli, EP; Bethge, M

Hierarchical Modeling of Local Image Features through Lp-Nested Symmetric Distributions

Sinz, F., Simoncelli, E., & Bethge, M. (2010). Hierarchical Modeling of Local Image Features through Lp-Nested Symmetric Distributions. In Y., Bengio, D., Schuurmans, J., Lafferty, C., Williams, & A., Culotta (Eds.), Advances in Neural Information Processing Systems 22 (pp. 1696-1704). Red Hook, NY, USA: Curran.

Item is 公開

表示: 全項目非表示: 全項目

基本情報

表示: 非表示:

アイテムのパーマリンク: https://hdl.handle.net/11858/00-001M-0000-0013-C0C8-7 版のパーマリンク: https://hdl.handle.net/21.11116/0000-0002-93C4-A

資料種別: 会議論文

ファイル

表示: ファイル

作成者

表示:

非表示:

作成者:
Sinz, F^{1, 2}, 著者
Simoncelli, EP, 著者
Bethge, M^{1, 2}, 著者

所属:
1Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497805
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794

内容説明

表示:

非表示:

キーワード: -

要旨: We introduce a new family of distributions, called Lp-nested symmetric distributions, whose densities are expressed in terms of a hierarchical cascade of Lp-
norms. This class generalizes the family of spherically and Lp-spherically symmetric distributions which have recently been successfully used for natural image modeling. Similar to those distributions it allows for a nonlinear mechanism
to reduce the dependencies between its variables. With suitable choices of the parameters and norms, this family includes the Independent Subspace Analysis (ISA) model as a special case, which has been proposed as a means of deriving
filters that mimic complex cells found in mammalian primary visual cortex. Lp-nested distributions are relatively easy to estimate and allow us to explore the variety of models between ISA and the Lp-spherically symmetric models. By fitting the generalized Lp-nested model to 8 by 8 image patches, we show that the subspaces obtained from ISA are in fact more dependent than the individual filter
coefficients within a subspace. When first applying contrast gain control as preprocessing, however, there are no dependencies left that could be exploited by ISA. This suggests that complex cell modeling can only be useful for redundancy reduction in larger image patches.

資料詳細

表示:

非表示:

言語:

日付: 出版: 2010-04

出版の状態: 出版

ページ: -

出版情報: -

目次: -

査読: -

識別子（DOI, ISBNなど）: BibTex参照ID: 6047

学位: -

訴訟

表示:

Project information

表示:

出版物 1

表示:

非表示:

出版物名: Advances in Neural Information Processing Systems 22

種別: 会議論文集

著者・編者:
Bengio, Y, 編集者
Schuurmans, D, 編集者
Lafferty, J, 編集者
Williams, C, 編集者
Culotta, A, 編集者

所属:
-

出版社, 出版地: Red Hook, NY, USA : Curran

ページ: - 巻号: - 通巻号: - 開始・終了ページ: 1696 - 1704 識別子（ISBN, ISSN, DOIなど）: ISBN: 978-1-615-67911-9

アイテム詳細

基本情報

ファイル

関連URL

作成者

内容説明

資料詳細

関連イベント

訴訟

Project information

出版物 1