Connectionists: A Neural System for Natural Scene Classification

[Stephen Grossberg]

The following article is now available at 
<http://www.cns.bu.edu/Profiles/Grossberg>http://www.cns.bu.edu/Profiles/Grossberg 
:

Grossberg, S. and Huang, T.-R.
ARTSCENE: A Neural System for Natural Scene Classification.
Journal of Vision, in press.

ABSTRACT
How do humans rapidly recognize a scene?  How can neural models 
capture this biological competence to achieve state-of-the-art scene 
classification? The ARTSCENE neural system classifies natural scene 
photographs by using multiple spatial scales to efficiently 
accumulate evidence for gist and texture. ARTSCENE embodies a 
coarse-to-fine Texture Size Ranking Principle whereby spatial 
attention processes multiple scales of scenic information, from 
global gist to local textures, to learn and recognize scenic 
properties. The model can incrementally learn and rapidly predict 
scene identity by gist information alone, and then accumulate learned 
evidence from scenic textures to refine this hypothesis. The model 
shows how texture-fitting allocations of spatial attention, called 
attentional shrouds, can facilitate scene recognition, particularly 
when they include a border of adjacent textures. Using grid gist plus 
three shroud textures on a benchmark photograph dataset, ARTSCENE 
discriminates 4 landscape scene categories (coast, forest, mountain 
and countryside) with up to 91.85% correct on a test set, outperforms 
alternative models in the literature which use biologically 
implausible computations, and outperforms component systems that use 
either gist or texture information alone. 

KEYWORDS: scene classification; gist; texture; spatial attention; 
coarse-to-fine processing; attentional shroud; multiple-scale 
processing; ARTMAP