CVNet - papers on visual recognition

CVNet (cvnet@skivs.ski.org)
Mon, 10 Jun 96 01:01:37 PDT

Date: Mon, 3 Jun 1996 22:24:04 -0400
From: Rajesh Rao <rao@skunk.cs.rochester.edu>
To: cvnet@skivs.ski.org, vision-list@teleosresearch.com
Cc: comp-neuro@smaug.bbb.caltech.edu, neuronet@tutkie.tut.ac.jp

cogneuro@ptolemy-ethernet.arc.nasa.gov, cogni-info@univ-lyon1.fr,
cogpsych@ripken.oit.unc.edu, cybsys-l@bingvaxu.cc.binghamton.edu,
inns-l%umdd.bitnet@pucc.princeton.edu, psyc@pucc.princeton.edu, rao
Subject: Papers available: Dynamic Visual Recognition

The following two related papers on dynamic models of visual
recognition are now available for retrieval via ftp. Comments and
suggestions welcome (This message has been cross-posted - my apologies
to those who receive it more than once).

-- 
Rajesh Rao                       Internet: rao@cs.rochester.edu
Dept. of Computer Science	 VOX:  (716) 275-2527              
University of Rochester          FAX:  (716) 461-2018
Rochester  NY  14627-0226        WWW:  http://www.cs.rochester.edu/u/rao/

===========================================================================

Dynamic Model of Visual Recognition Predicts Neural Response Properties In The Visual Cortex

Rajesh P.N. Rao and Dana H. Ballard

Technical Report 95.4 (revised) National Resource Laboratory for the study of Brain and Behavior University of Rochester, Rochester, NY 14627

(Also, Neural Computation - in review)

Abstract

The responses of visual cortical neurons during fixation tasks can be significantly modulated by stimuli from beyond the classical receptive field. Modulatory effects in neural responses have also been recently reported in a task where a monkey freely views a natural scene. In this paper, we describe a stochastic network model of visual recognition that explains these experimental observations by using a hierarchical form of the extended Kalman filter as given by the Minimum Description Length (MDL) principle. The model dynamically combines input-driven bottom-up signals with expectation-driven top-down signals to predict current recognition state. Synaptic weights in the model are adapted in a Hebbian manner according to a stochastic learning rule also derived from the MDL principle. The architecture of the model posits an active computational role for the reciprocal connections between adjoining visual cortical areas in determining neural response properties. In particular, the model demonstrates the possible role of feedback from higher cortical areas in mediating neurophysiological effects due to stimuli from beyond the classical receptive field. Simulations of the model are provided that help explain the experimental observations regarding neural responses in both free viewing and fixating conditions.

Retrieval information:

FTP-host: ftp.cs.rochester.edu FTP-pathname: /pub/u/rao/papers/dynmem.ps.Z WWW URL: ftp://ftp.cs.rochester.edu/pub/u/rao/papers/dynmem.ps.Z

32 pages; 534K compressed.

==========================================================================

A Class of Stochastic Models for Invariant Recognition, Motion, and Stereo

Rajesh P.N. Rao and Dana H. Ballard

(Submitted to NIPS 1996)

Abstract

We describe a general framework for modeling transformations in the image plane using a stochastic generative model. Algorithms that resemble the well-known Kalman filter are derived from the MDL principle for estimating both the generative weights and the current transformation state. The generative model is assumed to be implemented in cortical feedback pathways while the feedforward pathways implement an approximate inverse model to facilitate the estimation of current state. Using the above framework, we derive stochastic models for invariant recognition, motion estimation, and stereopsis, and present preliminary simulation results demonstrating recognition of objects in the presence of translations, rotations and scale changes.

Retrieval information:

FTP-host: ftp.cs.rochester.edu FTP-pathname: /pub/u/rao/papers/invar.ps.Z URL: ftp://ftp.cs.rochester.edu/pub/u/rao/papers/invar.ps.Z

7 pages; 430K compressed.

==========================================================================

Detailed anonymous ftp instructions:

>ftp ftp.cs.rochester.edu Connected to anon.cs.rochester.edu. 220 anon.cs.rochester.edu FTP server (Version wu-2.4(3)) ready.

Name: [type 'anonymous' here] 331 Guest login ok, send your complete e-mail address as password.

Password: [type your e-mail address here]

ftp> cd /pub/u/rao/papers/ ftp> get dynmem.ps ftp> get invar.ps ftp> bye