Distribution Distance Functions
|
|
- Magnus Nicholas Scott
- 5 years ago
- Views:
Transcription
1 COMP 875 November 10, 2009 Matthew O Meara
2 Question How similar are these?
3 Outline Motivation Protein Score Function Object Retrieval Kernel Machines 1 Motivation Protein Score Function Object Retrieval Kernel Machines 2 3
4 Protein Score Function Object Retrieval Kernel Machines Parametrization of H-bond geometry Parametrization of H-bond geometry H-bonds have 4 degrees of freedom H-bonds in Ubiquitin protein. H-bond geometry.
5 Protein Score Function Object Retrieval Kernel Machines Example H-bond Classification Decision Do H-bonds have different geometry in sheets and helices? Each point corresponds to a hydrogen bond: (Left) H-bonds in beta sheets. (Right) H-bonds in helices. AHDist is the bond length and cosbah is the cosine of the angle at the acceptor.
6 Outline Motivation Protein Score Function Object Retrieval Kernel Machines 1 Motivation Protein Score Function Object Retrieval Kernel Machines 2 3
7 Protein Score Function Object Retrieval Kernel Machines Image Retrieval Requires similarity measure Problem: Given new image return similar images from a database Browse through an image library (Rubner2000)
8 Protein Score Function Object Retrieval Kernel Machines Represent images as distributions Image features have relationships Inherent qualities: eg, color, texture, edges Spatial qualities: eg, where in the picture Visualizing shape context. (Grauman and Darrell 2004)
9 Protein Score Function Object Retrieval Kernel Machines Retrieve similar songs to a given song from a database Music Descriptors Mel-frequency cepstral coefficients (Spectrum of the spectrum scaled for humans) Pandora music genome descriptors etc. phoneme for security group Comparing music similarity (Typke2003) Pandora.com internet radio builds play lists from example songs
10 Outline Motivation Protein Score Function Object Retrieval Kernel Machines 1 Motivation Protein Score Function Object Retrieval Kernel Machines 2 3
11 ML Algorithms Require Kernels Protein Score Function Object Retrieval Kernel Machines Many machine Learning algorithms use kernels Unsupervised Learning: clustering nearest neighbor etc... Supervised Learning: support vector machines classification etc...
12 Bags of Features: Example Images can be reprented as histograms over texture features Extract features Learn visual vocabulary quantize features using visual vocabulary Julesz, 1981; Cula & Dana, 2001; Leung & Malik 2001; Mori, Belongie & Malik, 2001; Schmid 2001; Varma & Zisserman, 2002, 2003; Lazebnik, Schmid & Ponce, 2003, (slide from Lazebnik2009)
13 Outline Motivation 1 Motivation Protein Score Function Object Retrieval Kernel Machines 2 3
14 compare each feature separately Examples: χ 2 goodness of fit test Kullback Leibler divergence
15 χ 2 test for goodness of fit χ 2 test for goodness of fit Test null hypothesis that is no significant deviation from expected results. Let O and E be observed and expected distributions with n 1 degrees of freedom. n Let χ 2 (O i E i ) 2 =. E i i=1 Compare with χ 2 distribution to get goodness of fit Can be made symmetric
16 Kullback-Leibler Divergence Kullback-Leibler Divergence Let P and Q be distributions Support of P has to be subset of support of Q KL-divergence is the expected number of bit needed to encode Q given P. D KL (P Q) = P i log P i. Q i i It can be made symmetric.
17 Bin-Bin Comparison usefulness The good: Simple concepts Fast to evaluate O(n) Good at assessing equivlence lots of variants, well studied The bad: Sensitive to variance of signal All far things are very far
18 Bin-Bin vs Cross-Bin Metrics (upper)bin-bin comparison wrongly classifies left as begin less similar than right. (lower) Cross-Bin comparison correctly classifies left as being more similar than right (Rubner1997)
19 Quantization Error Quantization error is error due to splitting data into categories that is not seperable Example: Creating a cluster codebook with non separable data
20 Quantization Error Example Lighting and deformation exacerbate quantization error: Image pairs with deformation and lighting changes (Ling2007)
21 Outline Motivation 1 Motivation Protein Score Function Object Retrieval Kernel Machines 2 3
22 Earth Mover Distance Example Minimal flow from white signature to black signature (Rubner 2000)
23 Earth Mover Distance Definition Definition (Rubner 1997): Earth Mover Distance Represent each object as a signature S with centers {m i } and weights {w i }. The Earth Mover Distanc has the form EMD(S 1, S 2 ) = 1 fij fij d(m i, m j ) where the ground distances d(m i, m j ) are given and the flows f ij are solved for by an optomization problem.
24 Earth Mover Distance Flow Constraints EMD(S 1, S 2 ) = 1 fij fij d(m i, m j ) All flow must be positive, f ij 0. The flow to or from each center is at most the weight there, f ij w j f ij w i. i j The total flow is the weight of the lighter of S 1 and S 2, fij = min w i, w j. i j
25 EMD as a Max Flow problem EMD can be represented as a graph max flow problem (Ling2007)
26 EMD History Motivation Rediscovered many times (1942) Kantorovich proposes mass transport problem (1972) Mallows: Given two marginal distributions, find particular minimal joint distribution. (Levina, Bickel showed equivelence in 2001) (1996) Rubner et. al. propose EMD for image retrieval
27 EMD usefulness Motivation The good: Simple concept Results often seem natural Robust to noise The Bad: LP based solution has n 3 log(n) running time. (Orlin 1988)
28 Outline Motivation 1 Motivation Protein Score Function Object Retrieval Kernel Machines 2 3
29 Measure diffusion between histograms h 1 (x) and h 2 (x): The diffusion equation for the temperature field T is T t = 2 T x 2. Set the boundary conditions to be T (x, 0) = h 1 (x) h 2 (x) T (x, ) = 0. The solution is convolution with gaussian filters T (x, t) = T (x, 0) φ(x, t). Define diffusion distance between h 1 (x) and h 2 (x) to be K (h 1, h 2 ) = 0 T (x, t) dt.
30 Examples The columns are diffusion processes for difference histograms. Notice the left column diffuses faster. (Ling2006)
31 Outline Motivation 1 Motivation Protein Score Function Object Retrieval Kernel Machines 2 3
32 EMD Approximation by Embedding (Indyk and Thaper 2003) Ideas: Quantize with multilevel histogram Randomize bin offsets P(# bin p and q are in) d(p, q) Nearest neighbor via Locality Sensitive hashing
33 Example multilevel histogram 0 To compare point sets P and Q with minimum separation 1: Compute randomly offset multilevel distance histogram K (P, Q) = i,l 2 l v il (P) v il (Q) where v il gives the number of points in bin i of level l Multilevel histogram for orange and blue point sets. The numbers in
34 How LSH for Nearest Neighbor Search Preparation: Define randomly offset multilevel histogram V = {v il } Pick LSH parameters, range r R, and k random lines defined by a 1,..., a k V, and b 1,..., b k [0, r]. Preprocessing for each image in database: Compute coordinates x = {x il } Compute hash values h aj,b j For each test image: compute hashes = a j x+b j r look up images with same k hash values
35 Outline Motivation 1 Motivation Protein Score Function Object Retrieval Kernel Machines 2 3
36 Wavelet Approach Motivation EMD via Embedding looks like haar wavelet encoding. What about other wavelet basis? (Left)First 3 Haar Wavelets ( (Right)Daubechies4 father wavelet (
37 Approximation Using the Wavelet Domain Shirdhonkar and Jacobs achieve O(n) approximation using the wavelet domain. Duel Kantorovich-Rubinstein transhipment problem has wavelet domain representation with explicit solution, d(p) emd = λ 2 j(1+n/2) p λ Where p is difference histogram, p λ are its wavelet coefficients with shifts λ at scale j.
38 Comparison of Linear Approximations Shirdhonkar and Jacobs compared with their Wavelet EMD to EMD. Comparison over 100 random histograms.
39 Comparison of Linear Approximations Shirdhonkar and Jacobs compared with their Wavelet EMD to EMD. Comparison over SIMPLIcity database: 10 image classes with 100 images each Each image is in LAB color space with Euclidean ground distance Method Bounds Normalized Preproc. Compare ratio RMS Error time(s) time(ms) EMD Wavelet EMD % Indyk-Thaper %
40 Thanks Motivation Thanks! Questions?
Fast and Robust Earth Mover s Distances
Fast and Robust Earth Mover s Distances Ofir Pele and Michael Werman School of Computer Science and Engineering The Hebrew University of Jerusalem {ofirpele,werman}@cs.huji.ac.il Abstract We present a
More informationEarth Mover s Distance and The Applications
Earth Mover s Distance and The Applications Hu Ding Computer Science and Engineering, Michigan State University The Motivations It is easy to compare two single objects: the pairwise distance. For example:
More informationBag of Words Models. CS4670 / 5670: Computer Vision Noah Snavely. Bag-of-words models 11/26/2013
CS4670 / 5670: Computer Vision Noah Snavely Bag-of-words models Object Bag of words Bag of Words Models Adapted from slides by Rob Fergus and Svetlana Lazebnik 1 Object Bag of words Origin 1: Texture Recognition
More informationPatch Descriptors. CSE 455 Linda Shapiro
Patch Descriptors CSE 455 Linda Shapiro How can we find corresponding points? How can we find correspondences? How do we describe an image patch? How do we describe an image patch? Patches with similar
More informationCS6670: Computer Vision
CS6670: Computer Vision Noah Snavely Lecture 16: Bag-of-words models Object Bag of words Announcements Project 3: Eigenfaces due Wednesday, November 11 at 11:59pm solo project Final project presentations:
More informationLocal Features and Bag of Words Models
10/14/11 Local Features and Bag of Words Models Computer Vision CS 143, Brown James Hays Slides from Svetlana Lazebnik, Derek Hoiem, Antonio Torralba, David Lowe, Fei Fei Li and others Computer Engineering
More informationBag-of-features. Cordelia Schmid
Bag-of-features for category classification Cordelia Schmid Visual search Particular objects and scenes, large databases Category recognition Image classification: assigning a class label to the image
More informationAnnouncements. Recognition. Recognition. Recognition. Recognition. Homework 3 is due May 18, 11:59 PM Reading: Computer Vision I CSE 152 Lecture 14
Announcements Computer Vision I CSE 152 Lecture 14 Homework 3 is due May 18, 11:59 PM Reading: Chapter 15: Learning to Classify Chapter 16: Classifying Images Chapter 17: Detecting Objects in Images Given
More informationDiffusion Distance for Histogram Comparison
Diffusion Distance for Histogram Comparison Haibin Ling Center for Automation Research, Computer Science Department, University of Maryland College Park, MD, 20770, USA hbling@umiacs.umd.edu Kazunori Okada
More informationPreviously. Part-based and local feature models for generic object recognition. Bag-of-words model 4/20/2011
Previously Part-based and local feature models for generic object recognition Wed, April 20 UT-Austin Discriminative classifiers Boosting Nearest neighbors Support vector machines Useful for object recognition
More informationPatch Descriptors. EE/CSE 576 Linda Shapiro
Patch Descriptors EE/CSE 576 Linda Shapiro 1 How can we find corresponding points? How can we find correspondences? How do we describe an image patch? How do we describe an image patch? Patches with similar
More informationBy Suren Manvelyan,
By Suren Manvelyan, http://www.surenmanvelyan.com/gallery/7116 By Suren Manvelyan, http://www.surenmanvelyan.com/gallery/7116 By Suren Manvelyan, http://www.surenmanvelyan.com/gallery/7116 By Suren Manvelyan,
More informationPart-based and local feature models for generic object recognition
Part-based and local feature models for generic object recognition May 28 th, 2015 Yong Jae Lee UC Davis Announcements PS2 grades up on SmartSite PS2 stats: Mean: 80.15 Standard Dev: 22.77 Vote on piazza
More informationVisual Object Recognition
Perceptual and Sensory Augmented Computing Visual Object Recognition Tutorial Visual Object Recognition Bastian Leibe Computer Vision Laboratory ETH Zurich Chicago, 14.07.2008 & Kristen Grauman Department
More informationSupervised learning. y = f(x) function
Supervised learning y = f(x) output prediction function Image feature Training: given a training set of labeled examples {(x 1,y 1 ),, (x N,y N )}, estimate the prediction function f by minimizing the
More informationPart based models for recognition. Kristen Grauman
Part based models for recognition Kristen Grauman UT Austin Limitations of window-based models Not all objects are box-shaped Assuming specific 2d view of object Local components themselves do not necessarily
More informationLecture 6: Texture. Tuesday, Sept 18
Lecture 6: Texture Tuesday, Sept 18 Graduate students Problem set 1 extension ideas Chamfer matching Hierarchy of shape prototypes, search over translations Comparisons with Hausdorff distance, L1 on
More informationBeyond Bags of features Spatial information & Shape models
Beyond Bags of features Spatial information & Shape models Jana Kosecka Many slides adapted from S. Lazebnik, FeiFei Li, Rob Fergus, and Antonio Torralba Detection, recognition (so far )! Bags of features
More informationLecture 6: Multimedia Information Retrieval Dr. Jian Zhang
Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang NICTA & CSE UNSW COMP9314 Advanced Database S1 2007 jzhang@cse.unsw.edu.au Reference Papers and Resources Papers: Colour spaces-perceptual, historical
More informationNonparametric Clustering of High Dimensional Data
Nonparametric Clustering of High Dimensional Data Peter Meer Electrical and Computer Engineering Department Rutgers University Joint work with Bogdan Georgescu and Ilan Shimshoni Robust Parameter Estimation:
More informationIntroduction to object recognition. Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and others
Introduction to object recognition Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and others Overview Basic recognition tasks A statistical learning approach Traditional or shallow recognition
More informationTopology-Preserved Diffusion Distance for Histogram Comparison
Topology-Preserved Diffusion Distance for Histogram Comparison Wang Yan, Qiqi Wang, Qingshan Liu, Hanqing Lu, and Songde Ma National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy
More informationObject Classification Problem
HIERARCHICAL OBJECT CATEGORIZATION" Gregory Griffin and Pietro Perona. Learning and Using Taxonomies For Fast Visual Categorization. CVPR 2008 Marcin Marszalek and Cordelia Schmid. Constructing Category
More informationBeyond Bags of Features
: for Recognizing Natural Scene Categories Matching and Modeling Seminar Instructed by Prof. Haim J. Wolfson School of Computer Science Tel Aviv University December 9 th, 2015
More informationNonnegative matrix factorization for segmentation analysis
Nonnegative matrix factorization for segmentation analysis Roman Sandler Nonnegative matrix factorization for segmentation analysis Research thesis In Partial Fulfillment of the Requirements for the Degree
More informationLocal Features and Kernels for Classifcation of Texture and Object Categories: A Comprehensive Study
Local Features and Kernels for Classifcation of Texture and Object Categories: A Comprehensive Study J. Zhang 1 M. Marszałek 1 S. Lazebnik 2 C. Schmid 1 1 INRIA Rhône-Alpes, LEAR - GRAVIR Montbonnot, France
More informationSegmentation and Grouping April 19 th, 2018
Segmentation and Grouping April 19 th, 2018 Yong Jae Lee UC Davis Features and filters Transforming and describing images; textures, edges 2 Grouping and fitting [fig from Shi et al] Clustering, segmentation,
More informationShape Context Matching For Efficient OCR
Matching For Efficient OCR May 14, 2012 Matching For Efficient OCR Table of contents 1 Motivation Background 2 What is a? Matching s Simliarity Measure 3 Matching s via Pyramid Matching Matching For Efficient
More informationFeature Extractors. CS 188: Artificial Intelligence Fall Nearest-Neighbor Classification. The Perceptron Update Rule.
CS 188: Artificial Intelligence Fall 2007 Lecture 26: Kernels 11/29/2007 Dan Klein UC Berkeley Feature Extractors A feature extractor maps inputs to feature vectors Dear Sir. First, I must solicit your
More informationCS 343H: Honors AI. Lecture 23: Kernels and clustering 4/15/2014. Kristen Grauman UT Austin
CS 343H: Honors AI Lecture 23: Kernels and clustering 4/15/2014 Kristen Grauman UT Austin Slides courtesy of Dan Klein, except where otherwise noted Announcements Office hours Kim s office hours this week:
More informationCV as making bank. Intel buys Mobileye! $15 billion. Mobileye:
CV as making bank Intel buys Mobileye! $15 billion Mobileye: Spin-off from Hebrew University, Israel 450 engineers 15 million cars installed 313 car models June 2016 - Tesla left Mobileye Fatal crash car
More informationTexture. COS 429 Princeton University
Texture COS 429 Princeton University Texture What is a texture? Antonio Torralba Texture What is a texture? Antonio Torralba Texture What is a texture? Antonio Torralba Texture Texture is stochastic and
More informationDescriptors for CV. Introduc)on:
Descriptors for CV Content 2014 1.Introduction 2.Histograms 3.HOG 4.LBP 5.Haar Wavelets 6.Video based descriptor 7.How to compare descriptors 8.BoW paradigm 1 2 1 2 Color RGB histogram Introduc)on: Image
More informationShape Context Matching For Efficient OCR. Sudeep Pillai
Shape Context Matching For Efficient OCR Sudeep Pillai May 18, 2012 Contents 1 Introduction 2 1.1 Motivation................................... 2 1.2 Background................................... 2 1.2.1
More informationVisual words. Map high-dimensional descriptors to tokens/words by quantizing the feature space.
Visual words Map high-dimensional descriptors to tokens/words by quantizing the feature space. Quantize via clustering; cluster centers are the visual words Word #2 Descriptor feature space Assign word
More informationLecture: k-means & mean-shift clustering
Lecture: k-means & mean-shift clustering Juan Carlos Niebles and Ranjay Krishna Stanford Vision and Learning Lab 1 Recap: Image Segmentation Goal: identify groups of pixels that go together 2 Recap: Gestalt
More informationBeyond Mere Pixels: How Can Computers Interpret and Compare Digital Images? Nicholas R. Howe Cornell University
Beyond Mere Pixels: How Can Computers Interpret and Compare Digital Images? Nicholas R. Howe Cornell University Why Image Retrieval? World Wide Web: Millions of hosts Billions of images Growth of video
More informationA String Matching Approach for Visual Retrieval and Classification
A String Matching Approach for Visual Retrieval and Classification Mei-Chen Yeh Dept. of Electrical and Computer Engineering, University of California, Santa Barbara, USA meichen@umail.ucsb.edu Kwang-Ting
More informationMotion illusion, rotating snakes
Motion illusion, rotating snakes Local features: main components 1) Detection: Find a set of distinctive key points. 2) Description: Extract feature descriptor around each interest point as vector. x 1
More informationOutline. Segmentation & Grouping. Examples of grouping in vision. Grouping in vision. Grouping in vision 2/9/2011. CS 376 Lecture 7 Segmentation 1
Outline What are grouping problems in vision? Segmentation & Grouping Wed, Feb 9 Prof. UT-Austin Inspiration from human perception Gestalt properties Bottom-up segmentation via clustering Algorithms: Mode
More informationBeyond bags of features: Adding spatial information. Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba Adding spatial information Forming vocabularies from pairs of nearby features doublets
More informationEvaluation of Different Metrics for Shape Based Image Retrieval Using a New Contour Points Descriptor
Evaluation of Different Metrics for Shape Based Image Retrieval Using a New Contour Points Descriptor María-Teresa García Ordás, Enrique Alegre, Oscar García-Olalla, Diego García-Ordás University of León.
More informationImage Classification based on Saliency Driven Nonlinear Diffusion and Multi-scale Information Fusion Ms. Swapna R. Kharche 1, Prof.B.K.
Image Classification based on Saliency Driven Nonlinear Diffusion and Multi-scale Information Fusion Ms. Swapna R. Kharche 1, Prof.B.K.Chaudhari 2 1M.E. student, Department of Computer Engg, VBKCOE, Malkapur
More informationTA Section: Problem Set 4
TA Section: Problem Set 4 Outline Discriminative vs. Generative Classifiers Image representation and recognition models Bag of Words Model Part-based Model Constellation Model Pictorial Structures Model
More informationDistances and Kernels. Motivation
Distances and Kernels Amirshahed Mehrtash Motivation How similar? 1 Problem Definition Designing a fast system to measure the similarity il it of two images. Used to categorize images based on appearance.
More informationGenerative and discriminative classification techniques
Generative and discriminative classification techniques Machine Learning and Category Representation 013-014 Jakob Verbeek, December 13+0, 013 Course website: http://lear.inrialpes.fr/~verbeek/mlcr.13.14
More informationCEE598 - Visual Sensing for Civil Infrastructure Eng. & Mgmt.
CEE598 - Visual Sensing for Civil Infrastructure Eng. & Mgmt. Session 19 Object Recognition II Mani Golparvar-Fard Department of Civil and Environmental Engineering 3129D, Newmark Civil Engineering Lab
More informationCSE 573: Artificial Intelligence Autumn 2010
CSE 573: Artificial Intelligence Autumn 2010 Lecture 16: Machine Learning Topics 12/7/2010 Luke Zettlemoyer Most slides over the course adapted from Dan Klein. 1 Announcements Syllabus revised Machine
More informationBag of Words or Bag of Features. Lecture-16 (Slides Credit: Cordelia Schmid LEAR INRIA Grenoble)
Bag of Words or Bag of Features Lecture-16 (Slides Credit: Cordelia Schmid LEAR INRIA Grenoble) Contents Interest Point Detector Interest Point Descriptor K-means clustering Support Vector Machine (SVM)
More informationLecture: k-means & mean-shift clustering
Lecture: k-means & mean-shift clustering Juan Carlos Niebles and Ranjay Krishna Stanford Vision and Learning Lab Lecture 11-1 Recap: Image Segmentation Goal: identify groups of pixels that go together
More informationTagProp: Discriminative Metric Learning in Nearest Neighbor Models for Image Annotation
TagProp: Discriminative Metric Learning in Nearest Neighbor Models for Image Annotation Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek, Cordelia Schmid LEAR team, INRIA Rhône-Alpes, Grenoble, France
More informationVisuelle Perzeption für Mensch- Maschine Schnittstellen
Visuelle Perzeption für Mensch- Maschine Schnittstellen Vorlesung, WS 2009 Prof. Dr. Rainer Stiefelhagen Dr. Edgar Seemann Institut für Anthropomatik Universität Karlsruhe (TH) http://cvhci.ira.uka.de
More informationCMPSCI 670: Computer Vision! Grouping
CMPSCI 670: Computer Vision! Grouping University of Massachusetts, Amherst October 14, 2014 Instructor: Subhransu Maji Slides credit: Kristen Grauman and others Final project guidelines posted Milestones
More informationGoing nonparametric: Nearest neighbor methods for regression and classification
Going nonparametric: Nearest neighbor methods for regression and classification STAT/CSE 46: Machine Learning Emily Fox University of Washington May 8, 28 Locality sensitive hashing for approximate NN
More informationRaghuraman Gopalan Center for Automation Research University of Maryland, College Park
2D Shape Matching (and Object Recognition) Raghuraman Gopalan Center for Automation Research University of Maryland, College Park 1 Outline What is a shape? Part 1: Matching/ Recognition Shape contexts
More informationEECS 442 Computer vision. Object Recognition
EECS 442 Computer vision Object Recognition Intro Recognition of 3D objects Recognition of object categories: Bag of world models Part based models 3D object categorization Computer Vision: Algorithms
More informationCS 4495 Computer Vision. Segmentation. Aaron Bobick (slides by Tucker Hermans) School of Interactive Computing. Segmentation
CS 4495 Computer Vision Aaron Bobick (slides by Tucker Hermans) School of Interactive Computing Administrivia PS 4: Out but I was a bit late so due date pushed back to Oct 29. OpenCV now has real SIFT
More informationMachine Learning Crash Course
Machine Learning Crash Course Photo: CMU Machine Learning Department protests G20 Computer Vision James Hays Slides: Isabelle Guyon, Erik Sudderth, Mark Johnson, Derek Hoiem The machine learning framework
More informationFuzzy based Multiple Dictionary Bag of Words for Image Classification
Available online at www.sciencedirect.com Procedia Engineering 38 (2012 ) 2196 2206 International Conference on Modeling Optimisation and Computing Fuzzy based Multiple Dictionary Bag of Words for Image
More informationSupervised learning. y = f(x) function
Supervised learning y = f(x) output prediction function Image feature Training: given a training set of labeled examples {(x 1,y 1 ),, (x N,y N )}, estimate the prediction function f by minimizing the
More informationLocal Image Features
Local Image Features Computer Vision CS 143, Brown Read Szeliski 4.1 James Hays Acknowledgment: Many slides from Derek Hoiem and Grauman&Leibe 2008 AAAI Tutorial This section: correspondence and alignment
More informationAnalysis: TextonBoost and Semantic Texton Forests. Daniel Munoz Februrary 9, 2009
Analysis: TextonBoost and Semantic Texton Forests Daniel Munoz 16-721 Februrary 9, 2009 Papers [shotton-eccv-06] J. Shotton, J. Winn, C. Rother, A. Criminisi, TextonBoost: Joint Appearance, Shape and Context
More informationCase-Based Reasoning. CS 188: Artificial Intelligence Fall Nearest-Neighbor Classification. Parametric / Non-parametric.
CS 188: Artificial Intelligence Fall 2008 Lecture 25: Kernels and Clustering 12/2/2008 Dan Klein UC Berkeley Case-Based Reasoning Similarity for classification Case-based reasoning Predict an instance
More informationCS 188: Artificial Intelligence Fall 2008
CS 188: Artificial Intelligence Fall 2008 Lecture 25: Kernels and Clustering 12/2/2008 Dan Klein UC Berkeley 1 1 Case-Based Reasoning Similarity for classification Case-based reasoning Predict an instance
More informationGoing nonparametric: Nearest neighbor methods for regression and classification
Going nonparametric: Nearest neighbor methods for regression and classification STAT/CSE 46: Machine Learning Emily Fox University of Washington May 3, 208 Locality sensitive hashing for approximate NN
More informationToday. Main questions 10/30/2008. Bag of words models. Last time: Local invariant features. Harris corner detector: rotation invariant detection
Today Indexing with local features, Bag of words models Matching local features Indexing features Bag of words model Thursday, Oct 30 Kristen Grauman UT-Austin Main questions Where will the interest points
More informationLecture 12 Visual recognition
Lecture 12 Visual recognition Bag of words models for object recognition and classification Discriminative methods Generative methods Silvio Savarese Lecture 11 17Feb14 Challenges Variability due to: View
More informationTexture. Texture. 2) Synthesis. Objectives: 1) Discrimination/Analysis
Texture Texture D. Forsythe and J. Ponce Computer Vision modern approach Chapter 9 (Slides D. Lowe, UBC) Key issue: How do we represent texture? Topics: Texture segmentation Texture-based matching Texture
More informationLocal Image Features
Local Image Features Computer Vision Read Szeliski 4.1 James Hays Acknowledgment: Many slides from Derek Hoiem and Grauman&Leibe 2008 AAAI Tutorial Flashed Face Distortion 2nd Place in the 8th Annual Best
More informationBias-Variance Trade-off (cont d) + Image Representations
CS 275: Machine Learning Bias-Variance Trade-off (cont d) + Image Representations Prof. Adriana Kovashka University of Pittsburgh January 2, 26 Announcement Homework now due Feb. Generalization Training
More informationMachine Learning. Nonparametric methods for Classification. Eric Xing , Fall Lecture 2, September 12, 2016
Machine Learning 10-701, Fall 2016 Nonparametric methods for Classification Eric Xing Lecture 2, September 12, 2016 Reading: 1 Classification Representing data: Hypothesis (classifier) 2 Clustering 3 Supervised
More informationLeaf Classification from Boundary Analysis
Leaf Classification from Boundary Analysis Anne Jorstad AMSC 663 Midterm Progress Report Fall 2007 Advisor: Dr. David Jacobs, Computer Science 1 Outline Background, Problem Statement Algorithm Validation
More informationLocal features: detection and description. Local invariant features
Local features: detection and description Local invariant features Detection of interest points Harris corner detection Scale invariant blob detection: LoG Description of local patches SIFT : Histograms
More informationFast Indexing and Search. Lida Huang, Ph.D. Senior Member of Consulting Staff Magma Design Automation
Fast Indexing and Search Lida Huang, Ph.D. Senior Member of Consulting Staff Magma Design Automation Motivation Object categorization? http://www.cs.utexas.edu/~grauman/slides/jain_et_al_cvpr2008.ppt Motivation
More informationK-Nearest Neighbors. Jia-Bin Huang. Virginia Tech Spring 2019 ECE-5424G / CS-5824
K-Nearest Neighbors Jia-Bin Huang ECE-5424G / CS-5824 Virginia Tech Spring 2019 Administrative Check out review materials Probability Linear algebra Python and NumPy Start your HW 0 On your Local machine:
More informationInstance-level recognition part 2
Visual Recognition and Machine Learning Summer School Paris 2011 Instance-level recognition part 2 Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire d Informatique,
More informationTexton-based Texture Classification
Texton-based Texture Classification Laurens van der Maaten a Eric Postma a a MICC, Maastricht University P.O. Box 616, 6200 MD Maastricht, The Netherlands Abstract Over the last decade, several studies
More informationAdaptive Learning of an Accurate Skin-Color Model
Adaptive Learning of an Accurate Skin-Color Model Q. Zhu K.T. Cheng C. T. Wu Y. L. Wu Electrical & Computer Engineering University of California, Santa Barbara Presented by: H.T Wang Outline Generic Skin
More informationAutomatic Ranking of Images on the Web
Automatic Ranking of Images on the Web HangHang Zhang Electrical Engineering Department Stanford University hhzhang@stanford.edu Zixuan Wang Electrical Engineering Department Stanford University zxwang@stanford.edu
More informationKernels and Clustering
Kernels and Clustering Robert Platt Northeastern University All slides in this file are adapted from CS188 UC Berkeley Case-Based Learning Non-Separable Data Case-Based Reasoning Classification from similarity
More informationCS 2750: Machine Learning. Clustering. Prof. Adriana Kovashka University of Pittsburgh January 17, 2017
CS 2750: Machine Learning Clustering Prof. Adriana Kovashka University of Pittsburgh January 17, 2017 What is clustering? Grouping items that belong together (i.e. have similar features) Unsupervised:
More informationFeature Matching and Robust Fitting
Feature Matching and Robust Fitting Computer Vision CS 143, Brown Read Szeliski 4.1 James Hays Acknowledgment: Many slides from Derek Hoiem and Grauman&Leibe 2008 AAAI Tutorial Project 2 questions? This
More informationClassification: Feature Vectors
Classification: Feature Vectors Hello, Do you want free printr cartriges? Why pay more when you can get them ABSOLUTELY FREE! Just # free YOUR_NAME MISSPELLED FROM_FRIEND... : : : : 2 0 2 0 PIXEL 7,12
More informationHeeyoul (Henry) Choi. Dept. of Computer Science Texas A&M University
Heeyoul (Henry) Choi Dept. of Computer Science Texas A&M University hchoi@cs.tamu.edu Facial Action Coding System Overview Optic Flow Analysis Local Velocity Extraction Local Smoothing Holistic Analysis
More informationThree things everyone should know to improve object retrieval. Relja Arandjelović and Andrew Zisserman (CVPR 2012)
Three things everyone should know to improve object retrieval Relja Arandjelović and Andrew Zisserman (CVPR 2012) University of Oxford 2 nd April 2012 Large scale object retrieval Find all instances of
More informationTEXTURE CLASSIFICATION METHODS: A REVIEW
TEXTURE CLASSIFICATION METHODS: A REVIEW Ms. Sonal B. Bhandare Prof. Dr. S. M. Kamalapur M.E. Student Associate Professor Deparment of Computer Engineering, Deparment of Computer Engineering, K. K. Wagh
More informationVC 11/12 T14 Visual Feature Extraction
VC 11/12 T14 Visual Feature Extraction Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos Miguel Tavares Coimbra Outline Feature Vectors Colour Texture
More informationFrom Word Embeddings To Document Distances. Matt J. Kusner Yu Sun Nicholas I. Kolkin Kilian Q. Weinberger
From Word Embeddings To Document Distances Matt J. Kusner Yu Sun Nicholas I. Kolkin Kilian Q. Weinberger Goal: a distance between two documents? Applications document classification multi-lingual document
More informationNearest Neighbor with KD Trees
Case Study 2: Document Retrieval Finding Similar Documents Using Nearest Neighbors Machine Learning/Statistics for Big Data CSE599C1/STAT592, University of Washington Emily Fox January 22 nd, 2013 1 Nearest
More informationon learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015
on learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015 Vector visual representation Fixed-size image representation High-dim (100 100,000) Generic, unsupervised: BoW,
More informationImage classification Computer Vision Spring 2018, Lecture 18
Image classification http://www.cs.cmu.edu/~16385/ 16-385 Computer Vision Spring 2018, Lecture 18 Course announcements Homework 5 has been posted and is due on April 6 th. - Dropbox link because course
More informationSegmentation and Grouping April 21 st, 2015
Segmentation and Grouping April 21 st, 2015 Yong Jae Lee UC Davis Announcements PS0 grades are up on SmartSite Please put name on answer sheet 2 Features and filters Transforming and describing images;
More informationFast and Robust Earth Mover s Distances
Fast and Robust Earth Mover s Distances Ofir Pele The Hebrew University of Jerusalem ofirpele@cs.huji.ac.il Michael Werman The Hebrew University of Jerusalem werman@cs.huji.ac.il Abstract We present a
More informationThe goals of segmentation
Image segmentation The goals of segmentation Group together similar-looking pixels for efficiency of further processing Bottom-up process Unsupervised superpixels X. Ren and J. Malik. Learning a classification
More informationMACHINE LEARNING: CLUSTERING, AND CLASSIFICATION. Steve Tjoa June 25, 2014
MACHINE LEARNING: CLUSTERING, AND CLASSIFICATION Steve Tjoa kiemyang@gmail.com June 25, 2014 Review from Day 2 Supervised vs. Unsupervised Unsupervised - clustering Supervised binary classifiers (2 classes)
More informationMidterm Wed. Local features: detection and description. Today. Last time. Local features: main components. Goal: interest operator repeatability
Midterm Wed. Local features: detection and description Monday March 7 Prof. UT Austin Covers material up until 3/1 Solutions to practice eam handed out today Bring a 8.5 11 sheet of notes if you want Review
More informationCS 343: Artificial Intelligence
CS 343: Artificial Intelligence Kernels and Clustering Prof. Scott Niekum The University of Texas at Austin [These slides based on those of Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley.
More informationFeature descriptors and matching
Feature descriptors and matching Detections at multiple scales Invariance of MOPS Intensity Scale Rotation Color and Lighting Out-of-plane rotation Out-of-plane rotation Better representation than color:
More informationEfficient Kernels for Identifying Unbounded-Order Spatial Features
Efficient Kernels for Identifying Unbounded-Order Spatial Features Yimeng Zhang Carnegie Mellon University yimengz@andrew.cmu.edu Tsuhan Chen Cornell University tsuhan@ece.cornell.edu Abstract Higher order
More informationVisuelle Perzeption für Mensch- Maschine Schnittstellen
Visuelle Perzeption für Mensch- Maschine Schnittstellen Vorlesung, WS 2009 Prof. Dr. Rainer Stiefelhagen Dr. Edgar Seemann Institut für Anthropomatik Universität Karlsruhe (TH) http://cvhci.ira.uka.de
More information