“When” rather than “Whether”: Developmental Variable Selection Melissa Dominguez Robert Jacobs Department of Computer Science University of Rochester.

Slides:



Advertisements
Similar presentations
Efficient High-Resolution Stereo Matching using Local Plane Sweeps Sudipta N. Sinha, Daniel Scharstein, Richard CVPR 2014 Yongho Shin.
Advertisements

Chapter 2.
Cue Reliabilities and Cue Combinations Robert Jacobs Department of Brain and Cognitive Sciences University of Rochester.
Systems Analysis, Prototyping and Iteration Systems Analysis.
Automatic determination of skeletal age from hand radiographs of children Image Science Institute Utrecht University C.A.Maas.
Fitting: The Hough transform. Voting schemes Let each feature vote for all the models that are compatible with it Hopefully the noise features will not.
Chapter 4: Physical Development: Body, Brain, and Perception Perceptual Development By Kati Tumaneng (for Drs. Cook & Cook)
3D Human Body Pose Estimation from Monocular Video Moin Nabi Computer Vision Group Institute for Research in Fundamental Sciences (IPM)
COMPUTER AIDED DIAGNOSIS: FEATURE SELECTION Prof. Yasser Mostafa Kadah –
Student: Yao-Sheng Wang Advisor: Prof. Sheng-Jyh Wang ARTICULATED HUMAN DETECTION 1 Department of Electronics Engineering National Chiao Tung University.
December 5, 2013Computer Vision Lecture 20: Hidden Markov Models/Depth 1 Stereo Vision Due to the limited resolution of images, increasing the baseline.
Developmental Constraints Aid the Acquisition of Binocular Sensitivities by Melissa Dominguez, and Robert A. Jacobs Class presentation for CogSci260 Spring.
Fitting: The Hough transform
Relational Data Mining in Finance Haonan Zhang CFWin /04/2003.
Robust Real-time Object Detection by Paul Viola and Michael Jones ICCV 2001 Workshop on Statistical and Computation Theories of Vision Presentation by.
Tracking multiple independent targets: Evidence for a parallel tracking mechanism Zenon Pylyshyn and Ron Storm presented by Nick Howe.
Binocular Disparity points nearer than horopter have crossed disparity
Lecture 4: Perception and Cognition in Immersive Virtual Environments Dr. Xiangyu WANG.
A Novel 2D To 3D Image Technique Based On Object- Oriented Conversion.
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
Chapter 11 The Stages of Learning.
Computer Vision Systems for the Blind and Visually Disabled. STATS 19 SEM Talk 3. Alan Yuille. UCLA. Dept. Statistics and Psychology.
ENG4BF3 Medical Image Processing
Face Alignment Using Cascaded Boosted Regression Active Shape Models
A Genetic Algorithms Approach to Feature Subset Selection Problem by Hasan Doğu TAŞKIRAN CS 550 – Machine Learning Workshop Department of Computer Engineering.
A Local Adaptive Approach for Dense Stereo Matching in Architectural Scene Reconstruction C. Stentoumis 1, L. Grammatikopoulos 2, I. Kalisperakis 2, E.
Time Series Data Analysis - I Yaji Sripada. Dept. of Computing Science, University of Aberdeen2 In this lecture you learn What are Time Series? How to.
December 4, 2014Computer Vision Lecture 22: Depth 1 Stereo Vision Comparing the similar triangles PMC l and p l LC l, we get: Similarly, for PNC r and.
VIEWING THE WORLD IN COLOR. COLOR A psychological interpretation Based on wavelength, amplitude, and purity Humans can discriminate among c. 10 million.
1 Perception, Illusion and VR HNRS 299, Spring 2008 Lecture 8 Seeing Depth.
CISC Machine Learning for Solving Systems Problems Presented by: Alparslan SARI Dept of Computer & Information Sciences University of Delaware
The Influence of Feature Type, Feature Structure and Psycholinguistic Parameters on the Naming Performance of Semantic Dementia and Alzheimer’s Patients.
Binocular Stereo #1. Topics 1. Principle 2. binocular stereo basic equation 3. epipolar line 4. features and strategies for matching.
Chapter 8 – Information Processing Approach to cognitive development Based on computers - Hardware = physical structures - Software* = processes.
CS332 Visual Processing Department of Computer Science Wellesley College Binocular Stereo Vision Region-based stereo matching algorithms Properties of.
Fitting: The Hough transform
Individual Differences in Human-Computer Interaction HMI Yun Hwan Kang.
. Introduction NeuroVision™ NVC vision correction technology is a non-invasive, patient-specific treatment based on visual stimulation and facilitation.
Evaluating Perceptual Cue Reliabilities Robert Jacobs Department of Brain and Cognitive Sciences University of Rochester.
Automated Fingertip Detection
Click to add text Systems Analysis, Prototyping and Iteration.
Hand Gesture Recognition Using Haar-Like Features and a Stochastic Context-Free Grammar IEEE 高裕凱 陳思安.
RULES Patty Nordstrom Hien Nguyen. "Cognitive Skills are Realized by Production Rules"
Optimal Eye Movement Strategies In Visual Search.
1 Computational Vision CSCI 363, Fall 2012 Lecture 16 Stereopsis.
Grenoble Images Parole Signal Automatique Modeling of visual cortical processing to estimate binocular disparity Introduction - The objective is to estimate.
Lecture 8CSE Intro to Cognitive Science1 Interpreting Line Drawings II.
Image Quality Measures Omar Javed, Sohaib Khan Dr. Mubarak Shah.
A computational model of stereoscopic 3D visual saliency School of Electronic Information Engineering Tianjin University 1 Wang Bingren.
1 Computational Vision CSCI 363, Fall 2012 Lecture 18 Stereopsis III.
Computational Vision CSCI 363, Fall 2012 Lecture 17 Stereopsis II
RiskTeam/ Zürich, 6 July 1998 Andreas S. Weigend, Data Mining Group, Information Systems Department, Stern School of Business, NYU 2: 1 Nonlinear Models.
Correspondence and Stereopsis. Introduction Disparity – Informally: difference between two pictures – Allows us to gain a strong sense of depth Stereopsis.
Hough Transform CS 691 E Spring Outline Hough transform Homography Reading: FP Chapter 15.1 (text) Some slides from Lazebnik.
1שידור ווידיאו ואודיו ברשת האינטרנט Dr. Ofer Hadar Communication Systems Engineering Department Ben-Gurion University of the Negev URL:
April 21, 2016Introduction to Artificial Intelligence Lecture 22: Computer Vision II 1 Canny Edge Detector The Canny edge detector is a good approximation.
IMAGE PROCESSING is the use of computer algorithms to perform image process on digital images   It is used for filtering the image and editing the digital.
Summary of “Efficient Deep Learning for Stereo Matching”
Line Fitting James Hayes.
STEREOPSIS The Stereopsis Problem: Fusion and Reconstruction
Wadsworth, a division of Thomson Learning
Common Classification Tasks
Binocular Stereo Vision
Binocular Stereo Vision
Binocular Stereo Vision
JPEG Still Image Data Compression Standard
Image and Video Processing
Fourier Transform of Boundaries
Learning Theory Reza Shadmehr
4. Visual Sensory Systems
Presentation transcript:

“When” rather than “Whether”: Developmental Variable Selection Melissa Dominguez Robert Jacobs Department of Computer Science University of Rochester

Introduction Using human developmental theories as an inspiration for machine learning –Don’t use all variables at once –Focus on choice of when to include certain variables A system which uses this process to learn disparity sensitivities

Human Perceptual Development Humans are born with limited sensory and cognitive abilities Two main schools of thought about early limitations –Traditional view Immaturities are barriers to be overcome –“Less is More” view Early limitations are helpful

Less is More in vision Newborns have poor visual acuity –Improves approx. linearly to near adult levels by about 8 months of age Other visual skills are being acquired at the same time –Sensitivity to disparities around 4 months We propose that early poor acuity helps in acquisition of disparity sensitivity

Less is More and binocular disparity detection A richly detailed pair of pictures The same pair of pictures, blurred

Previous coarse to fine approaches Coarse to fine approaches –First search low resolution image pair –Then refine estimate with high resolution pair Marr and Poggio, 1979; Quam, 1986; Barnard, 1987; Iocchi and Konolidge, 1998 Previous approaches are processing strategies - not developmental sequences

Architecture

Left and Right Images 1 dimensional images –Horizontal and vertical disparities exist –Only horizontal mean depth Left Right

Binocular Energy Filters Make comparisons in the energy domain Based on neurophysiology Compute Gabor functions of left and right eye images

Adaptable Portion

All input at once Unstaged Model

Progressive models Developmental Model Inverse Developmental Model Input in stages during training

Random Model Still have 3 stages –Stage 1 consists of a randomly selected third of the input units –In subsequent stages add another randomly selected third of the input units –Stages consist of same inputs across data items

Data Solid Object Noisy Object Planar Stereogram

Procedures Conjugate gradient training procedure 10 runs of each model for each data set –35 iterations per run Stages of 10, 10, and 15 iterations Randomly generated training set Test sets had evenly spaced disparities –Randomly generated object size and location

Solid Object Learning Curve

Solid Object Results

Noisy Object Results

Planar Stereogram Results

Results (t-values)

Result summary Overall Developmental and Inverse Developmental models performed best Random and Unstaged models performed worst

Why does Developmental model have high variance?

Why do Developmental and Inverse Developmental models work best? –Limitations on initial input size? NO! Random model results show otherwise –Hypothesis: Important to combine features at same scale in early stages Important to proceed to neighboring scales in stages

–Prediction: F-CF-CMF or C-CF-CMF perform poorly Suitably designed developmental sequences can aid learning of complex vision tasks Development Aids Learning

Conclusions Performance of a system can be improved by judiciously choosing when to include each variable –Randomly staggering variables is not enough