Show simple item record

dc.contributor.authorGrossberg, Stephenen_US
dc.contributor.authorHuang, Tsung-Renen_US
dc.date.accessioned2011-11-14T18:17:07Z
dc.date.available2011-11-14T18:17:07Z
dc.date.issued2007-11en_US
dc.identifier.urihttps://hdl.handle.net/2144/1955
dc.description.abstractHow do humans rapidly recognize a scene? How can neural models capture this biological competence to achieve state-of-the-art scene classification? The ARTSCENE neural system classifies natural scene photographs by using multiple spatial scales to efficiently accumulate evidence for gist and texture. ARTSCENE embodies a coarse-to-fine Texture Size Ranking Principle whereby spatial attention processes multiple scales of scenic information, ranging from global gist to local properties of textures. The model can incrementally learn and predict scene identity by gist information alone and can improve performance through selective attention to scenic textures of progressively smaller size. ARTSCENE discriminates 4 landscape scene categories (coast, forest, mountain and countryside) with up to 91.58% correct on a test set, outperforms alternative models in the literature which use biologically implausible computations, and outperforms component systems that use either gist or texture information alone. Model simulations also show that adjacent textures form higher-order features that are also informative for scene recognition.en_US
dc.description.sponsorshipNational Science Foundation (NSF SBE-0354378); Office of Naval Research (N00014-01-1-0624)en_US
dc.language.isoen_USen_US
dc.publisherBoston University Center for Adaptive Systems and Department of Cognitive and Neural Systemsen_US
dc.relation.ispartofseriesBU CAS/CNS Technical Reports;CAS/CNS-TR-2007-017en_US
dc.rightsCopyright 2007 Boston University. Permission to copy without fee all or part of this material is granted provided that: 1. The copies are not made or distributed for direct commercial advantage; 2. the report title, author, document number, and release date appear, and notice is given that copying is by permission of BOSTON UNIVERSITY TRUSTEES. To copy otherwise, or to republish, requires a fee and / or special permission.en_US
dc.subjectScene classificationen_US
dc.subjectGisten_US
dc.subjectTextureen_US
dc.subjectSpatial attentionen_US
dc.subjectCoarse-to-fine processingen_US
dc.subjectAttentional shrouden_US
dc.subjectMultiple-scale processingen_US
dc.subjectARTMAPen_US
dc.titleARTSCENE: A Neural System for Natural Scene Classificationen_US
dc.typeTechnical Reporten_US
dc.rights.holderBoston University Trusteesen_US


Files in this item

This item appears in the following Collection(s)

Show simple item record