Attention as a Bayesian inference process

Sharat Chikkerur; Thomas Serre; Cheston Tan; Tomaso Poggio

doi:10.1117/12.876734

17 March 2011 Attention as a Bayesian inference process

Sharat Chikkerur, Thomas Serre, Cheston Tan, Tomaso Poggio

Proceedings Volume 7865, Human Vision and Electronic Imaging XVI; 786511 (2011) https://doi.org/10.1117/12.876734
Event: IS&T/SPIE Electronic Imaging, 2011, San Francisco Airport, California, United States

Abstract

David Marr famously defined vision as "knowing what is where by seeing". In the framework described here, attention is the inference process that solves the visual recognition problem of what is where. The theory proposes a computational role for attention and leads to a model that performs well in recognition tasks and that predicts some of the main properties of attention at the level of psychophysics and physiology. We propose an algorithmic implementation a Bayesian network that can be mapped into the basic functional anatomy of attention involving the ventral stream and the dorsal stream. This description integrates bottom-up, feature-based as well as spatial (context based) attentional mechanisms. We show that the Bayesian model predicts well human eye fixations (considered as a proxy for shifts of attention) in natural scenes, and can improve accuracy in object recognition tasks involving cluttered real world images. In both cases, we found that the proposed model can predict human performance better than existing bottom-up and top-down computational models.

Citation Download Citation

Sharat Chikkerur, Thomas Serre, Cheston Tan, and Tomaso Poggio "Attention as a Bayesian inference process", Proc. SPIE 7865, Human Vision and Electronic Imaging XVI, 786511 (17 March 2011); https://doi.org/10.1117/12.876734

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available