Approximations in the HMAX Model
Name
MIT-CSAIL-TR-2011-021.pdf
Size
943.37 KB
Format
Adobe PDF
Checksum (MD5)
b2d7789cb03b2fbfeab36d86682a3b83
Author(s)
Chikkerur, Sharat
Poggio, Tomaso
Advisor(s)
Tomaso Poggio
Date Issued
April 14, 2011
Series/Report no.
MIT-CSAIL-TR-2011-021
CBCL-298
Abstract
The HMAX model is a biologically motivated architecture for computer vision whose components are in close agreement with existing physiological evidence. The model is capable of achieving close to human level performance on several rapid object recognition tasks. However, the model is computationally bound and has limited engineering applications in its current form. In this report, we present several approximations in order to increase the efficiency of the HMAX model. We outline approximations at several levels of the hierarchy and empirically evaluate the trade-offs between efficiency and accuracy. We also explore ways to quantify the representation capacity of the model.
Subjects
object recognition, approximation
Terms of Use
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported
Persistent DSpace Link
