Computer Science > Computer Vision and Pattern Recognition
[Submitted on 15 Nov 2018 (v1), last revised 18 Sep 2020 (this version, v8)]
Title:A Neurodynamic model of Saliency prediction in V1
View PDFAbstract:Lateral connections in the primary visual cortex (V1) have long been hypothesized to be responsible of several visual processing mechanisms such as brightness induction, chromatic induction, visual discomfort and bottom-up visual attention (also named saliency). Many computational models have been developed to independently predict these and other visual processes, but no computational model has been able to reproduce all of them simultaneously. In this work we show that a biologically plausible computational model of lateral interactions of V1 is able to simultaneously predict saliency and all the aforementioned visual processes. Our model's (NSWAM) architecture is based on Pennachio's neurodynamic model of lateral connections of V1. It is defined as a network of firing rate neurons, sensitive to visual features such as brightness, color, orientation and scale. We tested NSWAM saliency predictions using images from several eye tracking datasets. We show that accuracy of predictions, using shuffled metrics, obtained by our architecture is similar to other state-of-the-art computational methods, particularly with synthetic images (CAT2000-Pattern & SID4VAM) which mainly contain low level features. Moreover, we outperform other biologically-inspired saliency models that are specifically designed to exclusively reproduce saliency. Hence, we show that our biologically plausible model of lateral connections can simultaneously explain different visual proceses present in V1 (without applying any type of training or optimization and keeping the same parametrization for all the visual processes). This can be useful for the definition of a unified architecture of the primary visual cortex.
Submission history
From: David Berga [view email][v1] Thu, 15 Nov 2018 12:11:24 UTC (6,792 KB)
[v2] Thu, 22 Nov 2018 11:34:37 UTC (6,901 KB)
[v3] Thu, 29 Nov 2018 17:57:33 UTC (6,902 KB)
[v4] Tue, 4 Dec 2018 16:21:19 UTC (7,902 KB)
[v5] Fri, 14 Dec 2018 18:04:06 UTC (7,941 KB)
[v6] Fri, 1 Feb 2019 17:45:10 UTC (7,938 KB)
[v7] Sun, 29 Sep 2019 22:19:01 UTC (7,991 KB)
[v8] Fri, 18 Sep 2020 20:36:01 UTC (5,863 KB)
References & Citations
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
Connected Papers (What is Connected Papers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.