Skip to main content

Object Recognition at Higher Regions of the Ventral Visual Stream via Dynamic Inference

Author(s): Sorooshyari, Siamak K; Sheng, Huanjie; Poor, H Vincent

To refer to this page use:
Abstract: The ventral visual stream (VVS) is a fundamental pathway involved in visual object identification and recognition. In this work, we present a hypothesis of a sequence of computations performed by the VVS during object recognition. The operations performed by the inferior temporal (IT) cortex are represented as not being akin to a neural-network, but rather in-line with a dynamic inference instantiation of the untangling notion. The presentation draws upon a technique for dynamic maximum a posteriori probability (MAP) sequence estimation based on the Viterbi algorithm. Simulation results are presented to show that the decoding portion of the architecture that is associated with the IT can effectively untangle object identity when presented with synthetic data. More importantly, we take a step forward in visual neuroscience by presenting a framework for an inference-based approach that is biologically inspired via attributes implicated in primate object recognition. The analysis will provide insight in explaining the exceptional proficiency of the VVS.
Electronic Publication Date: 23-Jun-2020
Citation: Sorooshyari, Siamak K, Sheng, Huanjie, Poor, H Vincent. (Object Recognition at Higher Regions of the Ventral Visual Stream via Dynamic Inference. Frontiers in Computational Neuroscience, 14 (10.3389/fncom.2020.00046
DOI: doi:10.3389/fncom.2020.00046
EISSN: 1662-5188
Type of Material: Journal Article
Journal/Proceeding Title: Frontiers in Computational Neuroscience
Version: Final published version. This is an open access article.

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.