What is it about?
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 analysis will provide insight in explaining the exceptional proficiency of the VVS.
Featured Image
Photo by jesse orrico on Unsplash
Why is it important?
Presents a framework for an inference-based approach that is biologically inspired via attributes implicated in primate object recognition. The introduced model is an alternative to neural network techniques employing max-pooling, and an alternative to machine learning approaches that consider object categorization rather than classification of object attributes during the recognition process.
Perspectives
Fundamental algorithmic themes such as maximum a posteriori probability (MAP) sequence estimation and the Viterbi algorithm had not been previously used to model or study the efficiency of the VVS.
Siamak Sorooshyari
Stanford University
Read the Original
This page is a summary of: Object Recognition at Higher Regions of the Ventral Visual Stream via Dynamic Inference, Frontiers in Computational Neuroscience, June 2020, Frontiers,
DOI: 10.3389/fncom.2020.00046.
You can read the full text:
Contributors
The following have contributed to this page
