Serial vs. parallel models of attention in visual search: accounting for benchmark RT-distributions

Rani Moran, Michael Zehetleitner, Heinrich René Liesefeld, Hermann J. Müller, Marius Usher

Research output: Contribution to journalArticlepeer-review

Abstract

Visual search is central to the investigation of selective visual attention. Classical theories propose that items are identified by serially deploying focal attention to their locations. While this accounts for set-size effects over a continuum of task difficulties, it has been suggested that parallel models can account for such effects equally well. We compared the serial Competitive Guided Search model with a parallel model in their ability to account for RT distributions and error rates from a large visual search data-set featuring three classical search tasks: 1) a spatial configuration search (2 vs. 5); 2) a feature-conjunction search; and 3) a unique feature search (Wolfe, Palmer & Horowitz Vision Research, 50(14), 1304-1311, 2010). In the parallel model, each item is represented by a diffusion to two boundaries (target-present/absent); the search corresponds to a parallel race between these diffusors. The parallel model was highly flexible in that it allowed both for a parametric range of capacity-limitation and for set-size adjustments of identification boundaries. Furthermore, a quit unit allowed for a continuum of search-quitting policies when the target is not found, with “single-item inspection” and exhaustive searches comprising its extremes. The serial model was found to be superior to the parallel model, even before penalizing the parallel model for its increased complexity. We discuss the implications of the results and the need for future studies to resolve the debate.

Original languageEnglish
Pages (from-to)1300-1315
Number of pages16
JournalPsychonomic Bulletin and Review
Volume23
Issue number5
DOIs
StatePublished - 1 Oct 2016

Keywords

  • Attention
  • Computational models
  • Model comparison
  • Parallel processing
  • RT distributions
  • Search termination
  • Serial processing
  • Visual search

Fingerprint

Dive into the research topics of 'Serial vs. parallel models of attention in visual search: accounting for benchmark RT-distributions'. Together they form a unique fingerprint.

Cite this