English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Top–down learning of low-level vision tasks

Jones, M., Sinha, P., Vetter, T., & Poggio, T. (1997). Top–down learning of low-level vision tasks. Current Biology, 7(12), 991-994. doi:10.1016/S0960-9822(06)00419-2.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-E9AA-E Version Permalink: http://hdl.handle.net/21.11116/0000-0005-E1F3-A
Genre: Journal Article

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Jones, MJ, Author
Sinha, P1, Author              
Vetter, T1, Author              
Poggio, T, Author              
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Perceptual tasks such as edge detection, image segmentation, lightness computation and estimation of three-dimensional structure are considered to be low-level or mid-level vision problems and are traditionally approached in a bottom–up, generic and hard-wired way. An alternative to this would be to take a top–down, object-class-specific and example-based approach. In this paper, we present a simple computational model implementing the latter approach. The results generated by our model when tested on edge-detection and view-prediction tasks for three-dimensional objects are consistent with human perceptual expectations. The model's performance is highly tolerant to the problems of sensor noise and incomplete input image information. Results obtained with conventional bottom–up strategies show much less immunity to these problems. We interpret the encouraging performance of our computational model as evidence in support of the hypothesis that the human visual system may learn to perform supposedly low-level perceptual tasks in a top–down fashion.

Details

show
hide
Language(s):
 Dates: 1997-12
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.1016/S0960-9822(06)00419-2
BibTex Citekey: 364
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Current Biology
  Other : Curr. Biol.
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: London, UK : Cell Press
Pages: - Volume / Issue: 7 (12) Sequence Number: - Start / End Page: 991 - 994 Identifier: ISSN: 0960-9822
CoNE: https://pure.mpg.de/cone/journals/resource/954925579107