Contextual Classification with Functional Max-Margin Markov Networks
|
|
- Nigel Allison
- 6 years ago
- Views:
Transcription
1 Contextual Classification with Functional Max-Margin Markov Networks Dan Munoz Nicolas Vandapel Drew Bagnell Martial Hebert
2 Geometry Estimation (Hoiem et al.) Sky Problem 3-D Point Cloud Classification Wall Vertical Vegetation Support Ground Our classifications Tree trunk 2
3 Room For Improvement 3
4 Approach: Improving CRF Learning Gradient descent (w) Boosting (h) Friedman et al. 2001, Ratliff et al Better learn models with high-order interactions + Efficiently handle large data & feature sets + Enable non-linear clique potentials 4
5 Pairwise model Conditional Random Fields y i Lafferty et al Labels x MAP Inference 5
6 Parametric Linear Model Weights Local features that describe label 6
7 Associative/Potts Potentials Labels Disagree 7
8 Overall Score Overall Score for a labeling y to all nodes 8
9 Iterate Learning Intuition Classify with current CRF model If (misclassified) φ( ) increase score φ( ) decrease score (Same update with edges) 9
10 Max-Margin Structured Prediction Taskar et al min w Best score from all labelings (+M) Score with ground truth labeling Ground truth labels Convex 10
11 Descending Direction (Objective) Labels from MAP inference Ground truth labels 11
12 Learned Model 12
13 Unit step-size, and λ = 0 Update Rule w t+1 += Ground truth Inferred 13
14 Iterate Verify Learning Intuition w t+1 += If (misclassified) φ( ) increase score φ( ) decrease score 14
15 1. Create training set: D Alternative Update From the misclassified nodes & edges D =, +1, -1, +1, -1 15
16 1. Create training set: D 2. Train regressor: h t Alternative Update D h t ( ) 16
17 1. Create training set: D 2. Train regressor: h 3. Augment model: Alternative Update (Before) 17
18 Functional M 3 N Summary Given features and labels for T iterations Classification with current model Create training set from misclassified cliques D Train regressor/classifier h t Augment model 18
19 Create training set Illustration D
20 Illustration Train regressor h t h 1 ( ) ϕ( ) = α 1 h 1 ( ) 20
21 Illustration Classification with current CRF model ϕ( ) = α 1 h 1 ( ) 21
22 Illustration Create training set D +1-1 ϕ( ) = α 1 h 1 ( ) 22
23 Illustration Train regressor h t h 2 ( ) ϕ( ) = α 1 h 1 ( )+α 2 h 2 ( ) 23
24 Stop Illustration ϕ( ) = α 1 h 1 ( )+α 2 h 2 ( ) 24
25 Boosted CRF Related Work Gradient Tree Boosting for CRFs Dietterich et al Boosted Random Fields Torralba et al Virtual Evidence Boosting for CRFs Liao et al Benefits of Max-Margin objective Do not need marginal probabilities (Robust) High-order interactions Kohli et al. 2007,
26 Using Higher Order Information Colored by elevation 26
27 Region Based Model 27
28 Region Based Model 28
29 Region Based Model Inference: graph-cut procedure P n Potts model (Kohli et al. 2007) 29
30 How To Train The Model Learning 1 30
31 How To Train The Model Learning (ignores features from clique c) 31
32 How To Train The Model Robust P n Potts Kohli et al β Learning 1 β 32
33 Experimental Analysis 3-D Point Cloud Classification Geometry Surface Estimation 33
34 Random Field Description Nodes: 3-D points Edges: 5-Nearest Neighbors Cliques: Two K-means segmentations Features [0,0,1] θ normal Local shape Orientation Elevation 34
35 Qualitative Comparisons Parametric Functional (this work) 35
36 Qualitative Comparisons Parametric Functional (this work) 36
37 Qualitative Comparisons Parametric Functional (this work) 37
38 Quantitative Results (1.2 M pts) Macro* AP: Parametric 64.3% Precision +24% +4% % Recall -1% Functional 71.5% % 0.93 Wire Pole/Trunk Façade Vegetation 38
39 Experimental Analysis 3-D Point Cloud Classification Geometry Surface Estimation 39
40 Random Field Description Nodes: Superpixels (Hoiem et al. 2007) Edges: (none) Cliques: 15 segmentations (Hoiem et al. 2007) More Robust Features (Hoiem et al. 2007) Perspective, color, texture, etc. 1,000 dimensional space 40
41 Quantitative Comparisons Parametric (Potts) Hoiem et al Functional (Potts) Functional (Robust Potts) 41
42 Qualitative Comparisons Parametric (Potts) Functional (Potts) 42
43 Qualitative Comparisons Parametric (Potts) Functional (Potts) Functional (Robust Potts) 43
44 Qualitative Comparisons Parametric (Potts) Hoiem et al Functional (Potts) Functional (Robust Potts) 44
45 Qualitative Comparisons Parametric (Potts) Hoiem et al Functional (Potts) Functional (Robust Potts) 45
46 Qualitative Comparisons Parametric (Potts) Hoiem et al Functional (Potts) Functional (Robust Potts) 46
47 Conclusion Effective max-margin learning of high-order CRFs Especially for large dimensional spaces Robust Potts interactions Easy to implement Future work Non-linear potentials (decision tree/random forest) New inference procedures: Komodakisand Paragios 2009 Ishikawa 2009 Gould et al Rother et al
48 Acknowledgements Thank you U. S. Army Research Laboratory Siebel Scholars Foundation S. K. Divalla, N. Ratliff, B. Becker Questions? 48
Contextual Classification with Functional Max- Margin Markov Networks
Research Showcase @ CMU Robotics Institute School of Computer Science 2009 Contextual Classification with Functional Max- Margin Markov Networks Daniel Munoz J. Andrew Bagnell Nicolas Vandapel Martial
More informationLearning Message-Passing Inference Machines for Structured Prediction
Learning -Passing Inference Machines for Structured Prediction Stéphane Ross Daniel Munoz Martial Hebert J. Andrew Bagnell The Robotics Institute, Carnegie Mellon University stephaneross@cmu.edu, {dmunoz,
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 informationSegmentation. Bottom up Segmentation Semantic Segmentation
Segmentation Bottom up Segmentation Semantic Segmentation Semantic Labeling of Street Scenes Ground Truth Labels 11 classes, almost all occur simultaneously, large changes in viewpoint, scale sky, road,
More informationMulti-Class Segmentation with Relative Location Prior
Multi-Class Segmentation with Relative Location Prior Stephen Gould, Jim Rodgers, David Cohen, Gal Elidan, Daphne Koller Department of Computer Science, Stanford University International Journal of Computer
More informationMarkov Networks in Computer Vision. Sargur Srihari
Markov Networks in Computer Vision Sargur srihari@cedar.buffalo.edu 1 Markov Networks for Computer Vision Important application area for MNs 1. Image segmentation 2. Removal of blur/noise 3. Stereo reconstruction
More informationarxiv: v1 [cs.cv] 20 Oct 2012
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials arxiv:1210.5644v1 [cs.cv] 20 Oct 2012 Philipp Krähenbühl Computer Science Department Stanford University philkr@cs.stanford.edu
More informationCombining Appearance and Structure from Motion Features for Road Scene Understanding
STURGESS et al.: COMBINING APPEARANCE AND SFM FEATURES 1 Combining Appearance and Structure from Motion Features for Road Scene Understanding Paul Sturgess paul.sturgess@brookes.ac.uk Karteek Alahari karteek.alahari@brookes.ac.uk
More informationMarkov Networks in Computer Vision
Markov Networks in Computer Vision Sargur Srihari srihari@cedar.buffalo.edu 1 Markov Networks for Computer Vision Some applications: 1. Image segmentation 2. Removal of blur/noise 3. Stereo reconstruction
More informationJoint 2D-3D Temporally Consistent Semantic Segmentation of Street Scenes
Joint 2D-3D Temporally Consistent Semantic Segmentation of Street Scenes Georgios Floros and Bastian Leibe UMIC Research Centre RWTH Aachen University, Germany {floros,leibe}@umic.rwth-aachen.de Abstract
More informationCS381V Experiment Presentation. Chun-Chen Kuo
CS381V Experiment Presentation Chun-Chen Kuo The Paper Indoor Segmentation and Support Inference from RGBD Images. N. Silberman, D. Hoiem, P. Kohli, and R. Fergus. ECCV 2012. 50 100 150 200 250 300 350
More informationAutomatic Photo Popup
Automatic Photo Popup Derek Hoiem Alexei A. Efros Martial Hebert Carnegie Mellon University What Is Automatic Photo Popup Introduction Creating 3D models from images is a complex process Time-consuming
More informationVisual Recognition: Examples of Graphical Models
Visual Recognition: Examples of Graphical Models Raquel Urtasun TTI Chicago March 6, 2012 Raquel Urtasun (TTI-C) Visual Recognition March 6, 2012 1 / 64 Graphical models Applications Representation Inference
More informationUndirected Graphical Models. Raul Queiroz Feitosa
Undirected Graphical Models Raul Queiroz Feitosa Pros and Cons Advantages of UGMs over DGMs UGMs are more natural for some domains (e.g. context-dependent entities) Discriminative UGMs (CRF) are better
More informationThe More the Merrier: Parameter Learning for Graphical Models with Multiple MAPs
The More the Merrier: Parameter Learning for Graphical Models with Multiple MAPs Franziska Meier fmeier@usc.edu U. of Southern California, 94 Bloom Walk, Los Angeles, CA 989 USA Amir Globerson amir.globerson@mail.huji.ac.il
More informationDecomposing a Scene into Geometric and Semantically Consistent Regions
Decomposing a Scene into Geometric and Semantically Consistent Regions Stephen Gould sgould@stanford.edu Richard Fulton rafulton@cs.stanford.edu Daphne Koller koller@cs.stanford.edu IEEE International
More informationLearning CRFs for Image Parsing with Adaptive Subgradient Descent
Learning CRFs for Image Parsing with Adaptive Subgradient Descent Honghui Zhang Jingdong Wang Ping Tan Jinglu Wang Long Quan The Hong Kong University of Science and Technology Microsoft Research National
More informationNON-ASSOCIATIVE MARKOV NETWORKS FOR 3D POINT CLOUD CLASSIFICATION
NON-ASSOCIATIVE MARKOV NETWORKS FOR 3D POINT CLOUD CLASSIFICATION Roman Shapovalov, Alexander Velizhev, Olga Barinova Graphics & Media Lab, Faculty of Computational Mathematics and Cybernetics Lomonosov
More informationD-Separation. b) the arrows meet head-to-head at the node, and neither the node, nor any of its descendants, are in the set C.
D-Separation Say: A, B, and C are non-intersecting subsets of nodes in a directed graph. A path from A to B is blocked by C if it contains a node such that either a) the arrows on the path meet either
More informationCRFs for Image Classification
CRFs for Image Classification Devi Parikh and Dhruv Batra Carnegie Mellon University Pittsburgh, PA 15213 {dparikh,dbatra}@ece.cmu.edu Abstract We use Conditional Random Fields (CRFs) to classify regions
More informationNon-associative Higher-Order Markov Networks for Point Cloud Classification
Non-associative Higher-Order Markov Networks for Point Cloud Classification Mohammad Najafi, Sarah Taghavi Namin, Mathieu Salzmann, and Lars Petersson Australian National University (ANU) NICTA,Canberra,Australia
More informationCS 558: Computer Vision 13 th Set of Notes
CS 558: Computer Vision 13 th Set of Notes Instructor: Philippos Mordohai Webpage: www.cs.stevens.edu/~mordohai E-mail: Philippos.Mordohai@stevens.edu Office: Lieb 215 Overview Context and Spatial Layout
More informationLearning CRFs using Graph Cuts
Appears in European Conference on Computer Vision (ECCV) 2008 Learning CRFs using Graph Cuts Martin Szummer 1, Pushmeet Kohli 1, and Derek Hoiem 2 1 Microsoft Research, Cambridge CB3 0FB, United Kingdom
More informationCS395T paper review. Indoor Segmentation and Support Inference from RGBD Images. Chao Jia Sep
CS395T paper review Indoor Segmentation and Support Inference from RGBD Images Chao Jia Sep 28 2012 Introduction What do we want -- Indoor scene parsing Segmentation and labeling Support relationships
More information6.034 Quiz 2, Spring 2005
6.034 Quiz 2, Spring 2005 Open Book, Open Notes Name: Problem 1 (13 pts) 2 (8 pts) 3 (7 pts) 4 (9 pts) 5 (8 pts) 6 (16 pts) 7 (15 pts) 8 (12 pts) 9 (12 pts) Total (100 pts) Score 1 1 Decision Trees (13
More informationRobust Higher Order Potentials for Enforcing Label Consistency
Robust Higher Order Potentials for Enforcing Label Consistency Pushmeet Kohli Microsoft Research Cambridge pkohli@microsoft.com L ubor Ladický Philip H. S. Torr Oxford Brookes University lladicky,philiptorr}@brookes.ac.uk
More informationContexts and 3D Scenes
Contexts and 3D Scenes Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem Administrative stuffs Final project presentation Nov 30 th 3:30 PM 4:45 PM Grading Three senior graders (30%)
More informationSegmentation in electron microscopy images
Segmentation in electron microscopy images Aurelien Lucchi, Kevin Smith, Yunpeng Li Bohumil Maco, Graham Knott, Pascal Fua. http://cvlab.epfl.ch/research/medical/neurons/ Outline Automated Approach to
More informationHIERARCHICAL CONDITIONAL RANDOM FIELD FOR MULTI-CLASS IMAGE CLASSIFICATION
HIERARCHICAL CONDITIONAL RANDOM FIELD FOR MULTI-CLASS IMAGE CLASSIFICATION Michael Ying Yang, Wolfgang Förstner Department of Photogrammetry, Bonn University, Bonn, Germany michaelyangying@uni-bonn.de,
More informationLearning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009
Learning and Inferring Depth from Monocular Images Jiyan Pan April 1, 2009 Traditional ways of inferring depth Binocular disparity Structure from motion Defocus Given a single monocular image, how to infer
More informationLearning What and How of Contextual Models for Scene Labeling
Learning What and How of Contextual Models for Scene Labeling Arpit Jain 1, Abhinav Gupta 2, and Larry S. Davis 1 1 University of Maryland College Park, MD, 20742 2 negie Mellon University, Pittsburgh,
More informationUsing Global Bag of Features Models in Random Fields for Joint Categorization and Segmentation of Objects
Using Global Bag of Features Models in Random Fields for Joint Categorization and Segmentation of Objects Dheeraj Singaraju René Vidal Center for Imaging Science, Johns Hopkins University, Baltimore MD
More informationComplex Prediction Problems
Problems A novel approach to multiple Structured Output Prediction Max-Planck Institute ECML HLIE08 Information Extraction Extract structured information from unstructured data Typical subtasks Named Entity
More informationHigh-Resolution Image Classification Integrating Spectral-Spatial-Location Cues by Conditional Random Fields
IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 9, SEPTEMBER 2016 4033 High-Resolution Image Classification Integrating Spectral-Spatial-Location Cues by Conditional Random Fields Ji Zhao, Student
More informationMulti-Class Segmentation with Relative Location Prior
International Journal of Computer Vision DOI 10.1007/s11263-008-0140-x Multi-Class Segmentation with Relative Location Prior Stephen Gould, Jim Rodgers, David Cohen, Gal Elidan, Daphne Koller Department
More informationUnsupervised Patch-based Context from Millions of Images
Carnegie Mellon University Research Showcase @ CMU Robotics Institute School of Computer Science 12-2011 Unsupervised Patch-based Context from Millions of Images Santosh K. Divvala Carnegie Mellon University
More informationFACADE SEGMENTATION WITH A STRUCTURED RANDOM FOREST
FACADE SEGMENTATION WITH A STRUCTURED RANDOM FOREST Kujtim Rahmani, Hai Huang, Helmut Mayer Bundeswehr University Munich, Institute for Applied Computer Science, Visual Computing, Neubiberg, Germany {kujtim.rahmani,
More informationMulti-Class Image Labeling with Top-Down Segmentation and Generalized Robust P N Potentials
FLOROS ET AL.: MULTI-CLASS IMAGE LABELING WITH TOP-DOWN SEGMENTATIONS 1 Multi-Class Image Labeling with Top-Down Segmentation and Generalized Robust P N Potentials Georgios Floros 1 floros@umic.rwth-aachen.de
More information10-701/15-781, Fall 2006, Final
-7/-78, Fall 6, Final Dec, :pm-8:pm There are 9 questions in this exam ( pages including this cover sheet). If you need more room to work out your answer to a question, use the back of the page and clearly
More informationCOMS 4771 Support Vector Machines. Nakul Verma
COMS 4771 Support Vector Machines Nakul Verma Last time Decision boundaries for classification Linear decision boundary (linear classification) The Perceptron algorithm Mistake bound for the perceptron
More informationSVM: Multiclass and Structured Prediction. Bin Zhao
SVM: Multiclass and Structured Prediction Bin Zhao Part I: Multi-Class SVM 2-Class SVM Primal form Dual form http://www.glue.umd.edu/~zhelin/recog.html Real world classification problems Digit recognition
More informationLearning Spatial Context: Using Stuff to Find Things
Learning Spatial Context: Using Stuff to Find Things Wei-Cheng Su Motivation 2 Leverage contextual information to enhance detection Some context objects are non-rigid and are more naturally classified
More informationSeparating Objects and Clutter in Indoor Scenes
Separating Objects and Clutter in Indoor Scenes Salman H. Khan School of Computer Science & Software Engineering, The University of Western Australia Co-authors: Xuming He, Mohammed Bennamoun, Ferdous
More informationMore on Learning. Neural Nets Support Vectors Machines Unsupervised Learning (Clustering) K-Means Expectation-Maximization
More on Learning Neural Nets Support Vectors Machines Unsupervised Learning (Clustering) K-Means Expectation-Maximization Neural Net Learning Motivated by studies of the brain. A network of artificial
More informationA Hierarchical Conditional Random Field Model for Labeling and Segmenting Images of Street Scenes
A Hierarchical Conditional Random Field Model for Labeling and Segmenting Images of Street Scenes Qixing Huang Stanford University huangqx@stanford.edu Mei Han Google Inc. meihan@google.com Bo Wu Google
More informationCan Similar Scenes help Surface Layout Estimation?
Can Similar Scenes help Surface Layout Estimation? Santosh K. Divvala, Alexei A. Efros, Martial Hebert Robotics Institute, Carnegie Mellon University. {santosh,efros,hebert}@cs.cmu.edu Abstract We describe
More informationSimultaneous Multi-class Pixel Labeling over Coherent Image Sets
Simultaneous Multi-class Pixel Labeling over Coherent Image Sets Paul Rivera Research School of Computer Science Australian National University Canberra, ACT 0200 Stephen Gould Research School of Computer
More informationThe exam is closed book, closed notes except your one-page (two-sided) cheat sheet.
CS 189 Spring 2015 Introduction to Machine Learning Final You have 2 hours 50 minutes for the exam. The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. No calculators or
More informationContext. CS 554 Computer Vision Pinar Duygulu Bilkent University. (Source:Antonio Torralba, James Hays)
Context CS 554 Computer Vision Pinar Duygulu Bilkent University (Source:Antonio Torralba, James Hays) A computer vision goal Recognize many different objects under many viewing conditions in unconstrained
More informationContexts and 3D Scenes
Contexts and 3D Scenes Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem Administrative stuffs Final project presentation Dec 1 st 3:30 PM 4:45 PM Goodwin Hall Atrium Grading Three
More information3-D Scene Analysis via Sequenced Predictions over Points and Regions
3-D Scene Analysis via Sequenced Predictions over Points and Regions Xuehan Xiong Daniel Munoz J. Andrew Bagnell Martial Hebert The Robotics Institute Carnegie Mellon University {xxiong, dmunoz, dbagnell,
More informationNatural Language Processing
Natural Language Processing Classification III Dan Klein UC Berkeley 1 Classification 2 Linear Models: Perceptron The perceptron algorithm Iteratively processes the training set, reacting to training errors
More informationEFFICIENT SEMANTIC SEGMENTATION OF MAN-MADE SCENES USING FULLY-CONNECTED CONDITIONAL RANDOM FIELD
EFFICIENT SEMANTIC SEGMENTATION OF MAN-MADE SCENES USING FULLY-CONNECTED CONDITIONAL RANDOM FIELD Weihao Li a, Michael Ying Yang a,b a TU Dresden, Computer Vision Lab Dresden, Dresden, Germany - weihao.li@mailbox.tu-dresden.de
More information3D Scene Understanding by Voxel-CRF
3D Scene Understanding by Voxel-CRF Byung-soo Kim University of Michigan bsookim@umich.edu Pushmeet Kohli Microsoft Research Cambridge pkohli@microsoft.com Silvio Savarese Stanford University ssilvio@stanford.edu
More informationarxiv: v2 [cs.cv] 1 Oct 2013
Structured learning of sum-of-submodular higher order energy functions Alexander Fix Thorsten Joachims Sam Park Ramin Zabih arxiv:309.752v2 [cs.cv] Oct 203 Abstract Submodular functions can be exactly
More informationDirection Matters: Depth Estimation with a Surface Normal Classifier
Direction Matters: Depth Estimation with a Surface Normal Classifier Christian Häne, L ubor Ladický, Marc Pollefeys Department of Computer Science ETH Zürich, Switzerland {christian.haene, lubor.ladicky,
More informationSemantic Labeling of 3D Point Clouds with Object Affordance for Robot Manipulation
Semantic Labeling of 3D Point Clouds with Object Affordance for Robot Manipulation David Inkyu Kim Gaurav S. Sukhatme Abstract When a robot is deployed it needs to understand the nature of its surroundings.
More informationGuiding Semi-Supervision with Constraint-Driven Learning
Guiding Semi-Supervision with Constraint-Driven Learning Ming-Wei Chang 1 Lev Ratinov 2 Dan Roth 3 1 Department of Computer Science University of Illinois at Urbana-Champaign Paper presentation by: Drew
More informationSensor Fusion for Semantic Segmentation of Urban Scenes
2015 IEEE International Conference on Robotics and Automation (ICRA) Washington State Convention Center Seattle, Washington, May 26-30, 2015 Sensor Fusion for Semantic Segmentation of Urban Scenes Richard
More informationRobust Higher Order Potentials for Enforcing Label Consistency
Int J Comput Vis (2009) 82: 302 324 DOI 10.1007/s11263-008-0202-0 Robust Higher Order Potentials for Enforcing Label Consistency Pushmeet Kohli L ubor Ladický Philip H.S. Torr Received: 17 August 2008
More informationComputer Vision Group Prof. Daniel Cremers. 4a. Inference in Graphical Models
Group Prof. Daniel Cremers 4a. Inference in Graphical Models Inference on a Chain (Rep.) The first values of µ α and µ β are: The partition function can be computed at any node: Overall, we have O(NK 2
More informationContext by Region Ancestry
Context by Region Ancestry Joseph J. Lim, Pablo Arbeláez, Chunhui Gu, and Jitendra Malik University of California, Berkeley - Berkeley, CA 94720 {lim,arbelaez,chunhui,malik}@eecs.berkeley.edu Abstract
More informationA study of classification algorithms using Rapidminer
Volume 119 No. 12 2018, 15977-15988 ISSN: 1314-3395 (on-line version) url: http://www.ijpam.eu ijpam.eu A study of classification algorithms using Rapidminer Dr.J.Arunadevi 1, S.Ramya 2, M.Ramesh Raja
More informationObject Recognition by Integrating Multiple Image Segmentations
Object Recognition by Integrating Multiple Image Segmentations Caroline Pantofaru 1, Cordelia Schmid 2, and Martial Hebert 1 1 The Robotics Institute, Carnegie Mellon University, USA 2 INRIA Grenoble,
More informationMMM-classification of 3D Range Data
MMM-classification of 3D Range Data Anuraag Agrawal, Atsushi Nakazawa, and Haruo Takemura Abstract This paper presents a method for accurately segmenting and classifying 3D range data into particular object
More informationUnsupervised discovery of category and object models. The task
Unsupervised discovery of category and object models Martial Hebert The task 1 Common ingredients 1. Generate candidate segments 2. Estimate similarity between candidate segments 3. Prune resulting (implicit)
More informationMarkov/Conditional Random Fields, Graph Cut, and applications in Computer Vision
Markov/Conditional Random Fields, Graph Cut, and applications in Computer Vision Fuxin Li Slides and materials from Le Song, Tucker Hermans, Pawan Kumar, Carsten Rother, Peter Orchard, and others Recap:
More informationFully-Connected CRFs with Non-Parametric Pairwise Potentials
Fully-Connected CRFs with Non-Parametric Pairwise Potentials Neill D. F. Campbell University College London Kartic Subr University College London Jan Kautz University College London Abstract Conditional
More informationFUSION OF MULTITEMPORAL AND MULTIRESOLUTION REMOTE SENSING DATA AND APPLICATION TO NATURAL DISASTERS
FUSION OF MULTITEMPORAL AND MULTIRESOLUTION REMOTE SENSING DATA AND APPLICATION TO NATURAL DISASTERS Ihsen HEDHLI, Josiane ZERUBIA INRIA Sophia Antipolis Méditerranée (France), Ayin team, in collaboration
More informationModels for grids. Computer vision: models, learning and inference. Multi label Denoising. Binary Denoising. Denoising Goal.
Models for grids Computer vision: models, learning and inference Chapter 9 Graphical Models Consider models where one unknown world state at each pixel in the image takes the form of a grid. Loops in the
More informationThree-Dimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients
ThreeDimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients Authors: Zhile Ren, Erik B. Sudderth Presented by: Shannon Kao, Max Wang October 19, 2016 Introduction Given an
More informationApplied Bayesian Nonparametrics 5. Spatial Models via Gaussian Processes, not MRFs Tutorial at CVPR 2012 Erik Sudderth Brown University
Applied Bayesian Nonparametrics 5. Spatial Models via Gaussian Processes, not MRFs Tutorial at CVPR 2012 Erik Sudderth Brown University NIPS 2008: E. Sudderth & M. Jordan, Shared Segmentation of Natural
More informationScene Segmentation with Conditional Random Fields Learned from Partially Labeled Images
Scene Segmentation with Conditional Random Fields Learned from Partially Labeled Images Jakob Verbeek and Bill Triggs INRIA and Laboratoire Jean Kuntzmann, 655 avenue de l Europe, 38330 Montbonnot, France
More informationCRF Based Point Cloud Segmentation Jonathan Nation
CRF Based Point Cloud Segmentation Jonathan Nation jsnation@stanford.edu 1. INTRODUCTION The goal of the project is to use the recently proposed fully connected conditional random field (CRF) model to
More informationAutomatic Dense Semantic Mapping From Visual Street-level Imagery
Automatic Dense Semantic Mapping From Visual Street-level Imagery Sunando Sengupta [1], Paul Sturgess [1], Lubor Ladicky [2], Phillip H.S. Torr [1] [1] Oxford Brookes University [2] Visual Geometry Group,
More informationScene Segmentation with Conditional Random Fields Learned from Partially Labeled Images
Scene Segmentation with Conditional Random Fields Learned from Partially Labeled Images Jakob Verbeek and Bill Triggs INRIA and Laboratoire Jean Kuntzmann, 655 avenue de l Europe, 38330 Montbonnot, France
More informationGeneric Face Alignment Using an Improved Active Shape Model
Generic Face Alignment Using an Improved Active Shape Model Liting Wang, Xiaoqing Ding, Chi Fang Electronic Engineering Department, Tsinghua University, Beijing, China {wanglt, dxq, fangchi} @ocrserv.ee.tsinghua.edu.cn
More informationLearning to Hash Logistic Regression for Fast 3D Scan Point Classification
Learning to Hash Logistic Regression for Fast 3D Scan Point Classification Jens Behley, Kristian Kersting, Dirk Schulz, Volker Steinhage and Armin B. Cremers Abstract Segmenting range data into semantic
More informationLEARNING BOUNDARIES WITH COLOR AND DEPTH. Zhaoyin Jia, Andrew Gallagher, Tsuhan Chen
LEARNING BOUNDARIES WITH COLOR AND DEPTH Zhaoyin Jia, Andrew Gallagher, Tsuhan Chen School of Electrical and Computer Engineering, Cornell University ABSTRACT To enable high-level understanding of a scene,
More informationSpatial Inference Machines
Spatial Inference Machines Roman Shapovalov Dmitry Vetrov Lomonosov Moscow State University http://bayesgroup.ru Pushmeet Kohli Microsoft Research Cambridge http://research.microsoft.com/ pkohli/ Abstract
More informationLearning Higher Order Potentials For MRFs
Learning Higher Order Potentials For MRFs Dinesh Khandelwal IIT Delhi Parag Singla IIT Delhi Chetan Arora IIIT Delhi Abstract Higher order MRF-MAP formulation has been shown to improve solutions in many
More informationUrban Scene Segmentation, Recognition and Remodeling. Part III. Jinglu Wang 11/24/2016 ACCV 2016 TUTORIAL
Part III Jinglu Wang Urban Scene Segmentation, Recognition and Remodeling 102 Outline Introduction Related work Approaches Conclusion and future work o o - - ) 11/7/16 103 Introduction Motivation Motivation
More informationCS5670: Computer Vision
CS5670: Computer Vision Noah Snavely Lecture 33: Recognition Basics Slides from Andrej Karpathy and Fei-Fei Li http://vision.stanford.edu/teaching/cs231n/ Announcements Quiz moved to Tuesday Project 4
More informationMachine Learning Classifiers and Boosting
Machine Learning Classifiers and Boosting Reading Ch 18.6-18.12, 20.1-20.3.2 Outline Different types of learning problems Different types of learning algorithms Supervised learning Decision trees Naïve
More informationarxiv: v1 [cs.cv] 7 Jan 2017
Urban Scene Segmentation with Laser-Constrained CRFs Charika De Alvis Lionel Ott Fabio Ramos arxiv:1701.01892v1 [cs.cv] 7 Jan 2017 Abstract Robots typically possess sensors of different modalities, such
More information3D Spatial Layout Propagation in a Video Sequence
3D Spatial Layout Propagation in a Video Sequence Alejandro Rituerto 1, Roberto Manduchi 2, Ana C. Murillo 1 and J. J. Guerrero 1 arituerto@unizar.es, manduchi@soe.ucsc.edu, acm@unizar.es, and josechu.guerrero@unizar.es
More informationStructured Learning. Jun Zhu
Structured Learning Jun Zhu Supervised learning Given a set of I.I.D. training samples Learn a prediction function b r a c e Supervised learning (cont d) Many different choices Logistic Regression Maximum
More informationThe exam is closed book, closed notes except your one-page (two-sided) cheat sheet.
CS 189 Spring 2015 Introduction to Machine Learning Final You have 2 hours 50 minutes for the exam. The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. No calculators or
More informationOn Parameter Learning in CRF-based Approaches to Object Class Image Segmentation
On Parameter Learning in CR-based Approaches to Object Class Image Segmentation Sebastian Nowozin 1, Peter V. Gehler 2, and Christoph H. Lampert 3 1 Microsoft Research Cambridge, UK, 2 ETH Zurich, Switzerland,
More informationMarkov Random Fields and Segmentation with Graph Cuts
Markov Random Fields and Segmentation with Graph Cuts Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem Administrative stuffs Final project Proposal due Oct 27 (Thursday) HW 4 is out
More informationClassification of laser and visual sensors using associative Markov networks
Universidade de São Paulo Biblioteca Digital da Produção Intelectual - BDPI Departamento de Mecatrônica e Sistemas Mecânicos - EP/PMR Comunicações em Eventos - EP/PMR 2012-01-20 Classification of laser
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 informationRegularization and Markov Random Fields (MRF) CS 664 Spring 2008
Regularization and Markov Random Fields (MRF) CS 664 Spring 2008 Regularization in Low Level Vision Low level vision problems concerned with estimating some quantity at each pixel Visual motion (u(x,y),v(x,y))
More informationDevelopment in Object Detection. Junyuan Lin May 4th
Development in Object Detection Junyuan Lin May 4th Line of Research [1] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection, CVPR 2005. HOG Feature template [2] P. Felzenszwalb,
More informationFast Edge Detection Using Structured Forests
Fast Edge Detection Using Structured Forests Piotr Dollár, C. Lawrence Zitnick [1] Zhihao Li (zhihaol@andrew.cmu.edu) Computer Science Department Carnegie Mellon University Table of contents 1. Introduction
More information3D Semantic Parsing of Large-Scale Indoor Spaces Supplementary Material
3D Semantic Parsing of Large-Scale Indoor Spaces Supplementar Material Iro Armeni 1 Ozan Sener 1,2 Amir R. Zamir 1 Helen Jiang 1 Ioannis Brilakis 3 Martin Fischer 1 Silvio Savarese 1 1 Stanford Universit
More informationMulti-Class Segmentation with Relative Location Prior
DOI 10.1007/s11263-008-0140-x Multi-Class Segmentation with Relative Location Prior Stephen Gould Jim Rodgers David Cohen Gal Elidan Daphne Koller Received: 26 September 2007 / Accepted: 17 April 2008
More informationObject Segmentation and Tracking in 3D Video With Sparse Depth Information Using a Fully Connected CRF Model
Object Segmentation and Tracking in 3D Video With Sparse Depth Information Using a Fully Connected CRF Model Ido Ofir Computer Science Department Stanford University December 17, 2011 Abstract This project
More informationIMPROVED FINE STRUCTURE MODELING VIA GUIDED STOCHASTIC CLIQUE FORMATION IN FULLY CONNECTED CONDITIONAL RANDOM FIELDS
IMPROVED FINE STRUCTURE MODELING VIA GUIDED STOCHASTIC CLIQUE FORMATION IN FULLY CONNECTED CONDITIONAL RANDOM FIELDS M. J. Shafiee, A. G. Chung, A. Wong, and P. Fieguth Vision & Image Processing Lab, Systems
More informationarxiv: v1 [cs.lg] 27 Mar 2014
Closed-Form Training of Conditional Random Fields for Large Scale Image Segmentation arxiv:1403.7057v1 [cs.lg] 27 Mar 2014 Alexander Kolesnikov IST Austria akolesnikov@ist.ac.at Vittorio Ferrari University
More information