Neural Models of Visual Attention John K. Tsotsos Center for Vision Research York University, Toronto, Canada Marc Pomplun Department of Computer Science.

Slides:



Advertisements
Similar presentations
Chapter 2: Marr’s theory of vision. Cognitive Science  José Luis Bermúdez / Cambridge University Press 2010 Overview Introduce Marr’s distinction between.
Advertisements

V1 Physiology. Questions Hierarchies of RFs and visual areas Is prediction equal to understanding? Is predicting the mean responses enough? General versus.
Visual Saliency: the signal from V1 to capture attention Li Zhaoping Head, Laboratory of natural intelligence Department of Psychology University College.
A Neural Model for Detecting and Labeling Motion Patterns in Image Sequences Marc Pomplun 1 Julio Martinez-Trujillo 2 Yueju Liu 2 Evgueni Simine 2 John.
September 2, 2014Computer Vision Lecture 1: Human Vision 1 Welcome to CS 675 – Computer Vision Fall 2014 Instructor: Marc Pomplun Instructor: Marc Pomplun.
Human (ERP and imaging) and monkey (cell recording) data together 1. Modality specific extrastriate cortex is modulated by attention (V4, IT, MT). 2. V1.
Laurent Itti: CS564 - Brain Theory and Artificial Intelligence. Didday Prey-Selector 1 Laurent Itti: CS564 - Brain Theory and Artificial Intelligence Lecture.
HMAX Models Architecture Jim Mutch March 31, 2010.
Attention I Attention Wolfe et al Ch 7. Dana said that most vision is agenda-driven. He introduced the slide where the people attended to the many weird.
Attention Wolfe et al Ch 7, Werner & Chalupa Ch 75, 78.
Features and Objects in Visual Processing
Attention, Awareness, and the Computational Theory of Surprise Research Qualifying Exam August 30 th, 2006.
Visual Search: finding a single item in a cluttered visual scene.
Visual Pathways W. W. Norton Primary cortex maintains distinct pathways – functional segregation M and P pathways synapse in different layers Ascending.
Experiments for Extra Credit Still available Go to to sign upwww.tatalab.ca.
Searching for the NCC We can measure all sorts of neural correlates of these processes…so we can see the neural correlates of consciousness right? So what’s.
Upcoming Stuff: Finish attention lectures this week No class Tuesday next week – What should you do instead? Start memory Thursday next week – Read Oliver.
Exam 1 week from today in class assortment of question types including written answers.
Michigan State University1 Visual Attention and Recognition Through Neuromorphic Modeling of “Where” and “What” Pathways Zhengping Ji Embodied Intelligence.
How does the visual system represent visual information? How does the visual system represent features of scenes? Vision is analytical - the system breaks.
COGNITIVE NEUROSCIENCE
Visual Attention More information in visual field than we can process at a given moment Solutions Shifts of Visual Attention related to eye movements Some.
Attention II Selective Attention & Visual Search.
Features and Object in Visual Processing. The Waterfall Illusion.
December 1, 2009Introduction to Cognitive Science Lecture 22: Neural Models of Mental Processes 1 Some YouTube movies: The Neocognitron Part I:
Laurent Itti: CS599 – Computational Architectures in Biological Vision, USC. Lecture 12: Visual Attention 1 Computational Architectures in Biological Vision,
Laurent Itti: CS599 – Computational Architectures in Biological Vision, USC Lecture 1: Overview & Introduction 1 Computational Architectures in Biological.
Chapter Four The Cognitive Approach I: History, Vision, and Attention.
Features and Object in Visual Processing. The Waterfall Illusion.
Michigan State University 1 “Saliency-Based Visual Attention” “Computational Modeling of Visual Attention”, Itti, Koch, (Nature Reviews – Neuroscience.
Instar Learning Law Adapted from lecture notes of the course CN510: Cognitive and Neural Modeling offered in the Department of Cognitive and Neural Systems.
Overview 1.The Structure of the Visual Cortex 2.Using Selective Tuning to Model Visual Attention 3.The Motion Hierarchy Model 4.Simulation Results 5.Conclusions.
The Cognitive Approach I: History, Vision, and Attention
Michael Arbib & Laurent Itti: CS664 – Spring Lecture 5: Visual Attention (bottom-up) 1 CS 664, USC Spring 2002 Lecture 5. Visual Attention (bottom-up)
Studying Visual Attention with the Visual Search Paradigm Marc Pomplun Department of Computer Science University of Massachusetts at Boston
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis Laurent Itti, Christof Koch, and Ernst Niebur IEEE PAMI, 1998.
 The most intelligent device - “Human Brain”.  The machine that revolutionized the whole world – “computer”.  Inefficiencies of the computer has lead.
Sensory systems basics. Sensing the external world.
1 Computational Vision CSCI 363, Fall 2012 Lecture 3 Neurons Central Visual Pathways See Reading Assignment on "Assignments page"
Cognition, Brain and Consciousness: An Introduction to Cognitive Neuroscience Edited by Bernard J. Baars and Nicole M. Gage 2007 Academic Press Chapter.
2 2  Background  Vision in Human Brain  Efficient Coding Theory  Motivation  Natural Pictures  Methodology  Statistical Characteristics  Models.
Feature Integration Theory Project guide: Amitabha Mukerjee Course: SE367 Presented by Harmanjit Singh.
黃文中 Introduction The Model Results Conclusion 2.
The architecture of the visual system: What is the grand design? April 12, 2010.
1 Towards a unified model of neocortex laminar cortical circuits for vision and cognition By: Fahime Sheikhzadeh.
Department of Psychology & The Human Computer Interaction Program Vision Sciences Society’s Annual Meeting, Sarasota, FL May 13, 2007 Jeremiah D. Still,
Advanced Analysis and Modeling Tools for Columnar- and Laminar-Level High- Resolution fMRI Data at 7+ Tesla Rainer Goebel Maastricht Brain Imaging Center.
Understanding V1 --- Saliency map and pre- attentive segmentation Li Zhaoping University College London, Psychology Lecture.
September 3, 2013Computer Vision Lecture 1: Human Vision 1 Welcome to CS 675 – Computer Vision Fall 2013 Instructor: Marc Pomplun Instructor: Marc Pomplun.
The Time Dimension for Scene Analysis DeLiang Wang Perception & Neurodynamics Lab The Ohio State University, USA.
Street Smarts: Visual Attention on the Go Alexander Patrikalakis May 13, XXX.
Binding problems and feature integration theory. Feature detectors Neurons that fire to specific features of a stimulus Pathway away from retina shows.
Laurent Itti: CS599 – Computational Architectures in Biological Vision, USC Lecture 12: Visual Attention 1 Computational Architectures in Biological.
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
An Oscillatory Correlation Approach to Scene Segmentation DeLiang Wang The Ohio State University.
1 Copyright © 2014 Elsevier Inc. All rights reserved. Chapter 19 Visual Network Moran Furman.
Eye Movements and Working Memory Marc Pomplun Department of Computer Science University of Massachusetts at Boston Homepage:
1 Perception and VR MONT 104S, Spring 2008 Lecture 3 Central Visual Pathways.
Biologically Inspired Vision-based Indoor Localization Zhihao Li, Ming Yang
March 31, 2016Introduction to Artificial Intelligence Lecture 16: Neural Network Paradigms I 1 … let us move on to… Artificial Neural Networks.
Attention to Orientation Results in an Inhibitory Surround in Orientation Space Acknowledgements Funding for this project was provided to MT through a.
National Taiwan Normal A System to Detect Complex Motion of Nearby Vehicles on Freeways C. Y. Fang Department of Information.
A Neurodynamical Cortical Model of Visual Attention and Invariant Object Recognition Gustavo Deco Edmund T. Rolls Vision Research, 2004.
Computational Vision --- a window to our brain
A bottom up visual saliency map in the primary visual cortex
Implementation of a Visual Attention Model
Computer Vision Lecture 2: Vision, Attention, and Eye Movements
Visual object recognition
Human vision: function
Toward a Great Class Project: Discussion of Stoianov & Zorzi’s Numerosity Model Psych 209 – 2019 Feb 14, 2019.
Presentation transcript:

Neural Models of Visual Attention John K. Tsotsos Center for Vision Research York University, Toronto, Canada Marc Pomplun Department of Computer Science University of Massachusetts at Boston

Müller (1873) Exner (1894) Wundt (1902) Pillsbury (1908) Broadbent 1958 (Early Selection) Deutsch, Deutsch & Norman 1963/68 (Late Selection) Treisman 1964 Milner 1974 * Grossberg (Adaptive Resonance Theory) * Treisman & Gelade 1980 (Feature Integration Theory) von der Malsburg (Correlation Theory) * Crick 1984 * Koch and Ullman 1985 Anderson and Van Essen 1987 (Shifter Circuits) * Sandon 1989 ‡ Wolfe et al (Guided Search 1.0, ) Phaf, Van der Heijden, Hudson 1990 (SLAM) Tsotsos et al (Selective Tuning) * ‡ Mozer 1991 (MORSEL) Ahmad 1991 (VISIT) * Olshausen, Anderson & Van Essen 1993 * ‡ Niebur, Koch et al * Desimone & Duncan 1995 (Biased Competition) * Postma 1995 (SCAN) * ‡ Schneider 1995 (VAM) * LaBerge 1995 * Itti & Koch 1998 ‡ Cave et al (FeatureGate) Theories/Models The number of models that address the neurobiology of visual attention is small (* in the list). The number that have real computational tests on actual images is even smaller (‡ in the list). However, many relevant ideas have appeared in psychological models. A selected historical perspective on the ideas important to the modelling task appears in the following slides.

Models of visual attention need to include solutions to or exhibit observed neurobiological/psychophysical performance for: Models of visual attention need to include solutions to or exhibit observed neurobiological/psychophysical performance for: F computational complexity of visual processes F information routing through the processing hierarchy F attentional control F time course of attentive modulation F single cell attentive modulation F attentive modulation in (apparently) all visual areas F suppressive surround effects F serial/”parallel” visual search performance F binding of features to objects Issues

Format of Overview Not all models are included, only those that have historical importance or that claim neuro-psycho relevance importance or that claim neuro-psycho relevance Due to space and time limits, each model is described only with: 1. key references 2. key ideas 3. neurobiological relationship (where possible) ( √ has supporting evidence X does not have supporting evidence X does not have supporting evidence ? open question) ? open question) Note that this can only be regarded as a partial review!

Koch and Ullman 1985 Koch, C., Ullman, S. (1985). Shifts in selective visual attention: Towards the underlying neural circuitry, Human Neurobiology 4, Key ideas: - saliency map (Treisman’s map) ? - winner-take-all competition √ (Findlay 1996, Lee et al. 1999) - WTA selects items to route to central representation X - inhibition of return for shifts ? - time to move attention proportional to logarithmic in distance between stimuli X (Krose & Julesz 1989) - no single cell modulations X

Anderson and Van Essen 1987 Shifter Circuits Anderson, C., Van Essen, D. (1987). Shifter Circuits: a computational strategy for dynamic aspects of visual processing, Proc. Natl. Academy Sci. USA 84: Key ideas: - information routing is accomplished by simple shifting circuits starting in the LGN and input layers of primate visual area V1 X the LGN and input layers of primate visual area V1 X - realignment is based on the preservation of spatial relationships - stages linked by diverging excitatory inputs. - direction of shift by inhibitory neurons that selectively suppress sets of ascending inputs. ascending inputs. - stages are grouped into small and large scale shifts. - control comes from pulvinar ?

Tsotsos Selective Tuning Model Tsotsos, J.K., Analyzing Vision at the Complexity Level, Behavioral and Brain Sciences 13-3, p , Tsotsos, J.K. (1993). An Inhibitory Beam for Attentional Selection, in Spatial Vision in Humans and Robots, ed. by L. Harris and M. Jenkin, p , Cambridge University Press. Tsotsos, J.K., Culhane, S., Wai, W., Lai, Y., Davis, N., Nuflo, F. (1995). Modeling visual attention via selective tuning, Artificial Intelligence 78(1-2),p Tsotsos, J.K. (1995). Towards a Computational Model of Visual Attention, in Early Vision and Beyond, ed. by T. Papathomas, C, Chubb, A. Gorea, E. Kowler, MIT Press/Bradford Books, p Tsotsos, J.K., Culhane, S., Cutzu, F., From Theoretical Foundations to a Hierarchical Circuit for Selective Attention, Visual Attention and Cortical Circuits, ed. by J. Braun, C. Koch & J. Davis, MIT Press (in press).

neuron ‘sees’ this receptive field subject ‘attends’ to single item Key ideas: - attention modulates neurons to earliest levels; wherever there is a many-to-one mapping √ many-to-one mapping √ - signal interference controlled by surround inhibition throughout processing network throughout processing network - task knowledge biases computations throughout processing network - inhibition of connections not units √ Hernandez-Peon, Scherrer, Jouvet (1956) √ Hernandez-Peon, Scherrer, Jouvet (1956) - attentional control is local, distributed and internal - competition is based on WTA (different form than previous models) (different form than previous models) - pyramid representation with reciprocal convergence and divergence √ Salin &Bullier(1995) √ Salin &Bullier(1995)

The basic idea (BBS 1990) not the same as von derMalsburg - only connections leading to interference are inhibited; other unattended ones left alone

processing pyramid inhibited pathways pass pathways unit of interest at top input √ Caputo & Guerra 1998 Bahcall & Kowler 1999 Vanduffel, Tootell, Orban 2000 Smith et al √ Kastner, De Weerd, Desimone, Ungerleider, 1998

top-down, coarse-to-fine WTA hierarchy for WTA hierarchy for incremental selection and incremental selection and localization localization unselected connections are unselected connections are inhibited inhibited WTA achieved through local gating networks Hierarchical Winner-Take-All Simulation

unit and connection in the interpretive network unit and connection in the gating network unit and connection in the top-down bias network layer +1 layer  -1 layer I Selection Circuits

Search for Blue Regions

Predictions from 1990 paper: attention in all visual areas, down to earliest competition can be biased by task inhibition of unselected connections within beam inhibitory surround impairs perception around attended item distractor effects depend on distractor-target separation

Olshausen, Anderson & Van Essen 1993 Olshausen, B., et al. (1993). A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information, J. of Neuroscience, 13(1): Key ideas: - implementation of shifter circuits - forms position and scale invariant representations at the output layer X - control neurons, originating in the pulvinar, dynamically modify synaptic weights of intracortical connections to achieve routing ? weights of intracortical connections to achieve routing ? - the topography of the selected portion of the visual field is preserved - uses Koch & Ullman mechanism (luminance saliency only) for selection - associative recognition at output layer at output layer

Olshausen seeks to achieve translation-rotation invariant recognition only attended item reaches output layer

Itti 1998 Itti, L., Koch, C., Niebur, E. (1998). A model for saliency-based visual attention for rapid scene analysis, IEEE Trans. Pattern Analysis and Machine Intelligence 20, Key ideas: - a newer implementation of Koch and Ullman’s scheme - fast and parallel pre-attentive extraction of visual features across 50 spatial maps (for orientation, intensity and color, at six spatial scales) maps (for orientation, intensity and color, at six spatial scales) - features are computed using linear filtering and center-surround structures - these features form a saliency map ? - Winner-Take-All neural network to select the most conspicuous image location location - inhibition-of-return mechanism to generate attentional shifts - saliency map topographically encodes for the local conspicuity in the visual scene, and controls where the focus of attention is currently deployed scene, and controls where the focus of attention is currently deployed

Conclusions Several ideas have endured: F Winner-Take-All for selection (competition) F Hierarchies F Inhibition of return to force serial search F Some kind of ‘gating’ process F Inhibitory surrounds F However, modeling seems to be still in its early days F Progress will depend on whether modelers and experimenters can work together