Why vision is not both hierarchical and feedforward

Simple item page
buir.contributor.authorClarke, Aaron
dc.citation.spage135en_US
dc.citation.volumeNumber8en_US
dc.contributor.authorHerzog, M.en_US
dc.contributor.authorClarke, Aaronen_US
dc.date.accessioned2020-04-09T17:17:04Z
dc.date.available2020-04-09T17:17:04Z
dc.date.issued2014
dc.departmentAysel Sabuncu Brain Research Center (BAM)en_US
dc.description.abstractIn classical models of object recognition, first, basic features (e.g., edges and lines) are analyzed by independent filters that mimic the receptive field profiles of V1 neurons. In a feedforward fashion, the outputs of these filters are fed to filters at the next processing stage, pooling information across several filters from the previous level, and so forth at subsequent processing stages. Low-level processing determines high-level processing. Information lost on lower stages is irretrievably lost. Models of this type have proven to be very successful in many fields of vision, but have failed to explain object recognition in general. Here, we present experiments that, first, show that, similar to demonstrations from the Gestaltists, figural aspects determine low-level processing (as much as the other way around). Second, performance on a single element depends on all the other elements in the visual scene. Small changes in the overall configuration can lead to large changes in performance. Third, grouping of elements is key. Only if we know how elements group across the entire visual field, we can determine performance on individual elements, i.e., challenging the classical stereotypical filtering approach, which is at the very heart of most vision models.en_US
dc.description.provenanceSubmitted by Onur Emek (onur.emek@bilkent.edu.tr) on 2020-04-09T17:17:04Z No. of bitstreams: 1 Bilkent-research-paper.pdf: 268963 bytes, checksum: ad2e3a30c8172b573b9662390ed2d3cf (MD5)en
dc.description.provenanceMade available in DSpace on 2020-04-09T17:17:04Z (GMT). No. of bitstreams: 1 Bilkent-research-paper.pdf: 268963 bytes, checksum: ad2e3a30c8172b573b9662390ed2d3cf (MD5) Previous issue date: 2014en
dc.identifier.doi10.3389/fncom.2014.00135en_US
dc.identifier.issn1662-5188
dc.identifier.urihttp://hdl.handle.net/11693/53576
dc.language.isoEnglishen_US
dc.publisherFrontiersen_US
dc.relation.isversionofhttps://doi.org/10.3389/fncom.2014.00135en_US
dc.source.titleFrontiers in Computational Neuroscienceen_US
dc.subjectFeedbacken_US
dc.subjectObject recognitionen_US
dc.subjectCrowdingen_US
dc.subjectVerniersen_US
dc.subjectGestalten_US
dc.titleWhy vision is not both hierarchical and feedforwarden_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Bilkent-research-paper.pdf
Size:
262.66 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Aysel Sabuncu Brain Research Center (BAM)