Cortical spatio-temporal dimensionality reduction for visual grouping

TL;DR

This paper introduces a geometric model and spectral clustering method for low-level object segmentation in visual stimuli, inspired by cortical processing mechanisms in mammals.

Contribution

It presents a novel geometric framework for modeling cortical connectivities and applies spectral clustering with anisotropic affinities for visual grouping.

Findings

Effective segmentation of visual stimuli using the proposed model

Spectral clustering with anisotropic affinities improves grouping accuracy

Neural plausibility of the model is discussed

Abstract

The visual systems of many mammals, including humans, is able to integrate the geometric information of visual stimuli and to perform cognitive tasks already at the first stages of the cortical processing. This is thought to be the result of a combination of mechanisms, which include feature extraction at single cell level and geometric processing by means of cells connectivity. We present a geometric model of such connectivities in the space of detected features associated to spatio-temporal visual stimuli, and show how they can be used to obtain low-level object segmentation. The main idea is that of defining a spectral clustering procedure with anisotropic affinities over datasets consisting of embeddings of the visual stimuli into higher dimensional spaces. Neural plausibility of the proposed arguments will be discussed.