Graph Cut based Inference with Co-occurrence Statistics. Ľubor Ladický, Chris Russell, Pushmeet Kohli, Philip Torr

Size: px
Start display at page:

Download "Graph Cut based Inference with Co-occurrence Statistics. Ľubor Ladický, Chris Russell, Pushmeet Kohli, Philip Torr"

Transcription

1 Graph Cut based Inference with Co-occurrence Statistics Ľubor Ladický, Chris Russell, Pushmeet Kohli, Philip Torr

2 Image labelling Problems Assign a label to each image pixel Geometry Estimation Image Denoising Object Segmentation Sky Building Tree Grass

3 Pairwise CRF models Standard CRF Energy Data term Smoothness term

4 Pairwise CRF models Standard CRF Energy Data term Smoothness term Restricted expressive power

5 Structures in CRF Taskar et al. 02 associative potentials Kohli et al. 08 segment consistency Woodford et al. 08 planarity constraint Vicente et al. 08 connectivity constraint Nowozin & Lampert 09 connectivity constraint Roth & Black 09 field of experts Ladický et al. 09 consistency over several scales Woodford et al. 09 marginal probability Delong et al. 10 label occurrence costs

6 Pairwise CRF models Standard CRF Energy for Object Segmentation Local context Cannot encode global consistency of labels!!

7 Detection Suppression If we have 1000 categories (detectors), and each detector produces 1 fp every 10 images, we will have 100 false alarms per image pretty much garbage [Torralba et al. 10, Leibe & Schiele 09, Barinova et al. 10] chair table car keyboard road table road mage from Torralba et al. 10

8 Encoding Co-occurrence Co-occurrence is a powerful cue [Heitz et al. '08] [Rabinovich et al. 07] Thing Thing Stuff - Stuff Stuff - Thing [ Images from Rabinovich et al. 07 ]

9 Encoding Co-occurrence Co-occurrence is a powerful cue [Heitz et al. '08] [Rabinovich et al. 07] Thing Thing Stuff - Stuff Stuff - Thing Proposed solutions : 1. Csurka et al Hard decision for label estimation 2. Torralba et al GIST based unary potential 3. Rabinovich et al Full-connected CRF [ Images from Rabinovich et al. 07 ]

10 So... What properties should these global co-occurence potentials have?

11 1. No hard decisions Desired properties

12 Desired properties 1. No hard decisions Incorporation in probabilistic framework Unlikely possibilities are not completely ruled out

13 Desired properties 1. No hard decisions 2. Invariance to region size

14 Desired properties 1. No hard decisions 2. Invariance to region size Cost for occurrence of {people, house, road etc.. } invariant to image area

15 Desired properties 1. No hard decisions 2. Invariance to region size The only possible solution : L(x)={,, } Local context Global context Cost defined over the assigned labels L(x)

16 Desired properties 1. No hard decisions 2. Invariance to region size 3. Parsimony simple solutions preferred L(x)={ aeroplane, tree, flower, building, boat, grass, sky } L(x)={ building, tree, grass, sky }

17 Desired properties 1. No hard decisions 2. Invariance to region size 3. Parsimony simple solutions preferred 4. Efficiency

18 Desired properties 1. No hard decisions 2. Invariance to region size 3. Parsimony simple solutions preferred 4. Efficiency a) Memory requirements as O(n) with the image size and number or labels b) Inference tractable

19 Previous work Torralba et al.(2003) Gist-based unary potentials Rabinovich et al.(2007) - complete pairwise graphs Csurka et al.(2008) - hard estimation of labels present

20 Related work Zhu & Yuille 1996 MDL prior Bleyer et al Surface Stereo MDL prior Hoiem et al D Layout CRF MDL Prior C(x) = K L(x) Delong et al label occurence cost C(x) = Σ L K L δ L (x)

21 Related work Zhu & Yuille 1996 MDL prior Bleyer et al Surface Stereo MDL prior Hoiem et al D Layout CRF MDL Prior C(x) = K L(x) Delong et al label occurence cost C(x) = Σ L K L δ L (x) All special cases of our model

22 Inference Pairwise CRF Energy

23 Inference IP formulation (Schlesinger 73)

24 Inference Pairwise CRF Energy with co-occurence

25 Inference IP formulation with co-occurence

26 Inference IP formulation with co-occurence Pairwise CRF cost Pairwise CRF constaints

27 Inference IP formulation with co-occurence Co-occurence cost

28 Inference IP formulation with co-occurence Inclusion constraints

29 Inference IP formulation with co-occurence Exclusion constraints

30 Inference LP relaxation Relaxed constraints

31 Inference LP relaxation Very Slow! 80 x 50 subsampled image takes 20 minutes

32 Inference: Our Contribution Pairwise representation One auxiliary variable Z 2 L Infinite pairwise costs if x i Z [see technical report] *Solvable using standard methods: BP, TRW etc.

33 Inference: Our Contribution Pairwise representation One auxiliary variable Z 2 L Infinite pairwise costs if x i Z [see technical report] *Solvable using standard methods: BP, TRW etc. Relatively faster but still computationally expensive!

34 Inference using Moves Graph Cut based move making algorithms [Boykov et al. 01] Series of locally optimal moves Each move reduces energy Optimal move by minimizing submodular function Current Solution Search Neighbourhood Move Space (t) : 2 N N L Number of Variables Number of Labels Space of Solutions (x) : L N α-expansion transformation function

35 Inference using Moves Graph Cut based move making algorithms [Boykov, Veksler, Zabih. 01] α-expansion transformation function

36 Inference using Moves Co-occurence representation Label indicator functions

37 Inference using Moves Move Energy Cost of current label set

38 Inference using Moves Move Energy Decomposition to α-dependent and α-independent part α-independent α-dependent

39 Inference using Moves Move Energy Decomposition to α-dependent and α-independent part Either α or all labels in the image after the move

40 Inference using Moves Move Energy submodular non-submodular

41 Inference Move Energy non-submodular Non-submodular energy overestimated by E'(t) E'(t) = E(t) for current solution E'(t) E(t) for any other labelling

42 Inference Move Energy non-submodular Non-submodular energy overestimated by E'(t) E'(t) = E(t) for current solution E'(t) E(t) for any other labelling Occurrence - tight

43 Inference Move Energy non-submodular Non-submodular energy overestimated by E'(t) E'(t) = E(t) for current solution E'(t) E(t) for any other labelling Co-occurrence overestimation

44 Inference Move Energy non-submodular Non-submodular energy overestimated by E'(t) E'(t) = E(t) for current solution E'(t) E(t) for any other labelling General case [See the paper]

45 Inference Move Energy non-submodular Non-submodular energy overestimated by E'(t) E'(t) = E(t) for current solution E'(t) E(t) for any other labelling Quadratic representation

46 Application: Object Segmentation Standard MRF model for Object Segmentation Label based Costs Cost defined over the assigned labels L(x)

47 Training of label based potentials Label set costs Approximated by 2 nd order representation Indicator variables for occurrence of each label

48 Methods Segment CRF Experiments Segment CRF + Co-occurrence Potential Associative HCRF [Ladický et al. 09] Associative HCRF + Co-occurrence Potential Datasets MSRC-21 Number of Images: 591 Number of Classes: 21 Training Set: 50% Test Set: 50% PASCAL VOC 2009 Number of Images: 1499 Number of Classes: 21 Training Set: 50% Test Set: 50%

49 MSRC - Qualitative

50 VOC 2010-Qualitative

51 Quantitative Results MSRC-21 PASCAL VOC 2009

52 Summary and further work Incorporated label based potentials in CRFs Proposed feasible inference Open questions Optimal training method for co-occurence Bounds of graph cut based inference Questions?

Pushmeet Kohli Microsoft Research

Pushmeet Kohli Microsoft Research Pushmeet Kohli Microsoft Research E(x) x in {0,1} n Image (D) [Boykov and Jolly 01] [Blake et al. 04] E(x) = c i x i Pixel Colour x in {0,1} n Unary Cost (c i ) Dark (Bg) Bright (Fg) x* = arg min E(x)

More information

Graph Cut based Inference with Co-occurrence Statistics

Graph Cut based Inference with Co-occurrence Statistics Graph Cut based Inference with Co-occurrence Statistics Lubor Ladicky 1,3, Chris Russell 1,3, Pushmeet Kohli 2, and Philip H.S. Torr 1 1 Oxford Brookes 2 Microsoft Research Abstract. Markov and Conditional

More information

Discrete Inference and Learning Lecture 3

Discrete Inference and Learning Lecture 3 Discrete Inference and Learning Lecture 3 MVA 2017 2018 h

More information

Inference Methods for CRFs with Co-occurrence Statistics

Inference Methods for CRFs with Co-occurrence Statistics Noname manuscript No. (will be inserted by the editor) Inference Methods for CRFs with Co-occurrence Statistics L ubor Ladický 1 Chris Russell 1 Pushmeet Kohli Philip H. S. Torr the date of receipt and

More information

Inference Methods for CRFs with Co-occurrence Statistics

Inference Methods for CRFs with Co-occurrence Statistics Int J Comput Vis (2013) 103:213 225 DOI 10.1007/s11263-012-0583-y Inference Methods for CRFs with Co-occurrence Statistics L ubor Ladický Chris Russell Pushmeet Kohli Philip H. S. Torr Received: 21 January

More information

Part 6: Structured Prediction and Energy Minimization (1/2)

Part 6: Structured Prediction and Energy Minimization (1/2) Part 6: Structured Prediction and Energy Minimization (1/2) Providence, 21st June 2012 Prediction Problem Prediction Problem y = f (x) = argmax y Y g(x, y) g(x, y) = p(y x), factor graphs/mrf/crf, g(x,

More information

Markov Random Fields for Computer Vision (Part 1)

Markov Random Fields for Computer Vision (Part 1) Markov Random Fields for Computer Vision (Part 1) Machine Learning Summer School (MLSS 2011) Stephen Gould stephen.gould@anu.edu.au Australian National University 13 17 June, 2011 Stephen Gould 1/23 Pixel

More information

Making the Right Moves: Guiding Alpha-Expansion using Local Primal-Dual Gaps

Making the Right Moves: Guiding Alpha-Expansion using Local Primal-Dual Gaps Making the Right Moves: Guiding Alpha-Expansion using Local Primal-Dual Gaps Dhruv Batra TTI Chicago dbatra@ttic.edu Pushmeet Kohli Microsoft Research Cambridge pkohli@microsoft.com Abstract 5 This paper

More information

A Graph Cut Algorithm for Higher-order Markov Random Fields

A Graph Cut Algorithm for Higher-order Markov Random Fields A Graph Cut Algorithm for Higher-order Markov Random Fields Alexander Fix Cornell University Aritanan Gruber Rutgers University Endre Boros Rutgers University Ramin Zabih Cornell University Abstract Higher-order

More information

Generalized Roof Duality for Pseudo-Boolean Optimization

Generalized Roof Duality for Pseudo-Boolean Optimization Generalized Roof Duality for Pseudo-Boolean Optimization Fredrik Kahl Petter Strandmark Centre for Mathematical Sciences, Lund University, Sweden {fredrik,petter}@maths.lth.se Abstract The number of applications

More information

MAP Estimation Algorithms in Computer Vision - Part II

MAP Estimation Algorithms in Computer Vision - Part II MAP Estimation Algorithms in Comuter Vision - Part II M. Pawan Kumar, University of Oford Pushmeet Kohli, Microsoft Research Eamle: Image Segmentation E() = c i i + c ij i (1- j ) i i,j E: {0,1} n R 0

More information

Higher-Order Clique Reduction Without Auxiliary Variables

Higher-Order Clique Reduction Without Auxiliary Variables Higher-Order Clique Reduction Without Auxiliary Variables Hiroshi Ishikawa Department of Computer Science and Engineering Waseda University Okubo 3-4-1, Shinjuku, Tokyo, Japan hfs@waseda.jp Abstract We

More information

Pushmeet Kohli. Microsoft Research Cambridge. IbPRIA 2011

Pushmeet Kohli. Microsoft Research Cambridge. IbPRIA 2011 Pushmeet Kohli Microsoft Research Cambridge IbPRIA 2011 2:30 4:30 Labelling Problems Graphical Models Message Passing 4:30 5:00 - Coffee break 5:00 7:00 - Graph Cuts Move Making Algorithms Speed and Efficiency

More information

On Partial Optimality in Multi-label MRFs

On Partial Optimality in Multi-label MRFs On Partial Optimality in Multi-label MRFs P. Kohli 1 A. Shekhovtsov 2 C. Rother 1 V. Kolmogorov 3 P. Torr 4 1 Microsoft Research Cambridge 2 Czech Technical University in Prague 3 University College London

More information

Rounding-based Moves for Semi-Metric Labeling

Rounding-based Moves for Semi-Metric Labeling Rounding-based Moves for Semi-Metric Labeling M. Pawan Kumar, Puneet K. Dokania To cite this version: M. Pawan Kumar, Puneet K. Dokania. Rounding-based Moves for Semi-Metric Labeling. Journal of Machine

More information

Truncated Max-of-Convex Models Technical Report

Truncated Max-of-Convex Models Technical Report Truncated Max-of-Convex Models Technical Report Pankaj Pansari University of Oxford The Alan Turing Institute pankaj@robots.ox.ac.uk M. Pawan Kumar University of Oxford The Alan Turing Institute pawan@robots.ox.ac.uk

More information

Learning Graph Laplacian for Image Segmentation

Learning Graph Laplacian for Image Segmentation Learning Graph Laplacian for Image Segmentation EN4: Image processing Sergey Milyaev Radiophysics Department Voronezh State University, Voronezh, Russia sergey.milyaev@gmail.com Olga Barinova Department

More information

On Partial Optimality in Multi-label MRFs

On Partial Optimality in Multi-label MRFs Pushmeet Kohli 1 Alexander Shekhovtsov 2 Carsten Rother 1 Vladimir Kolmogorov 3 Philip Torr 4 pkohli@microsoft.com shekhovt@cmp.felk.cvut.cz carrot@microsoft.com vnk@adastral.ucl.ac.uk philiptorr@brookes.ac.uk

More information

Higher-Order Clique Reduction in Binary Graph Cut

Higher-Order Clique Reduction in Binary Graph Cut CVPR009: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Miami Beach, Florida. June 0-5, 009. Hiroshi Ishikawa Nagoya City University Department of Information and Biological

More information

Integrating Local Classifiers through Nonlinear Dynamics on Label Graphs with an Application to Image Segmentation

Integrating Local Classifiers through Nonlinear Dynamics on Label Graphs with an Application to Image Segmentation Integrating Local Classifiers through Nonlinear Dynamics on Label Graphs with an Application to Image Segmentation Yutian Chen Andrew Gelfand Charless C. Fowlkes Max Welling Bren School of Information

More information

Learning with Structured Inputs and Outputs

Learning with Structured Inputs and Outputs Learning with Structured Inputs and Outputs Christoph H. Lampert IST Austria (Institute of Science and Technology Austria), Vienna Microsoft Machine Learning and Intelligence School 2015 July 29-August

More information

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials Philipp Krähenbühl and Vladlen Koltun Stanford University Presenter: Yuan-Ting Hu 1 Conditional Random Field (CRF) E x I = φ u

More information

Part 7: Structured Prediction and Energy Minimization (2/2)

Part 7: Structured Prediction and Energy Minimization (2/2) Part 7: Structured Prediction and Energy Minimization (2/2) Colorado Springs, 25th June 2011 G: Worst-case Complexity Hard problem Generality Optimality Worst-case complexity Integrality Determinism G:

More information

A note on the primal-dual method for the semi-metric labeling problem

A note on the primal-dual method for the semi-metric labeling problem A note on the primal-dual method for the semi-metric labeling problem Vladimir Kolmogorov vnk@adastral.ucl.ac.uk Technical report June 4, 2007 Abstract Recently, Komodakis et al. [6] developed the FastPD

More information

Transformation of Markov Random Fields for Marginal Distribution Estimation

Transformation of Markov Random Fields for Marginal Distribution Estimation Transformation of Markov Random Fields for Marginal Distribution Estimation Masaki Saito Takayuki Okatani Tohoku University, Japan {msaito, okatani}@vision.is.tohoku.ac.jp Abstract This paper presents

More information

Submodular Maximization and Diversity in Structured Output Spaces

Submodular Maximization and Diversity in Structured Output Spaces Submodular Maximization and Diversity in Structured Output Spaces Adarsh Prasad Virginia Tech, UT Austin adarshprasad27@gmail.com Stefanie Jegelka UC Berkeley stefje@eecs.berkeley.edu Dhruv Batra Virginia

More information

A Generative Perspective on MRFs in Low-Level Vision Supplemental Material

A Generative Perspective on MRFs in Low-Level Vision Supplemental Material A Generative Perspective on MRFs in Low-Level Vision Supplemental Material Uwe Schmidt Qi Gao Stefan Roth Department of Computer Science, TU Darmstadt 1. Derivations 1.1. Sampling the Prior We first rewrite

More information

Higher-order Graph Cuts

Higher-order Graph Cuts ACCV2014 Area Chairs Workshop Sep. 3, 2014 Nanyang Technological University, Singapore 1 Higher-order Graph Cuts Hiroshi Ishikawa Department of Computer Science & Engineering Waseda University Labeling

More information

Minimizing Count-based High Order Terms in Markov Random Fields

Minimizing Count-based High Order Terms in Markov Random Fields EMMCVPR 2011, St. Petersburg Minimizing Count-based High Order Terms in Markov Random Fields Thomas Schoenemann Center for Mathematical Sciences Lund University, Sweden Abstract. We present a technique

More information

Intelligent Systems:

Intelligent Systems: Intelligent Systems: Undirected Graphical models (Factor Graphs) (2 lectures) Carsten Rother 15/01/2015 Intelligent Systems: Probabilistic Inference in DGM and UGM Roadmap for next two lectures Definition

More information

Advanced Structured Prediction

Advanced Structured Prediction Advanced Structured Prediction Editors: Sebastian Nowozin Microsoft Research Cambridge, CB1 2FB, United Kingdom Peter V. Gehler Max Planck Insitute for Intelligent Systems 72076 Tübingen, Germany Jeremy

More information

Inference for Order Reduction in Markov Random Fields

Inference for Order Reduction in Markov Random Fields Inference for Order Reduction in Markov Random Fields Andre C. Gallagher Eastman Kodak Company andre.gallagher@kodak.com Dhruv Batra Toyota Technological Institute at Chicago ttic.uchicago.edu/ dbatra

More information

Revisiting Uncertainty in Graph Cut Solutions

Revisiting Uncertainty in Graph Cut Solutions Revisiting Uncertainty in Graph Cut Solutions Daniel Tarlow Dept. of Computer Science University of Toronto dtarlow@cs.toronto.edu Ryan P. Adams School of Engineering and Applied Sciences Harvard University

More information

Probabilistic Graphical Models & Applications

Probabilistic Graphical Models & Applications Probabilistic Graphical Models & Applications Learning of Graphical Models Bjoern Andres and Bernt Schiele Max Planck Institute for Informatics The slides of today s lecture are authored by and shown with

More information

Decision Tree Fields

Decision Tree Fields Sebastian Nowozin, arsten Rother, Shai agon, Toby Sharp, angpeng Yao, Pushmeet Kohli arcelona, 8th November 2011 Introduction Random Fields in omputer Vision Markov Random Fields (MRF) (Kindermann and

More information

Introduction To Graphical Models

Introduction To Graphical Models Peter Gehler Introduction to Graphical Models Introduction To Graphical Models Peter V. Gehler Max Planck Institute for Intelligent Systems, Tübingen, Germany ENS/INRIA Summer School, Paris, July 2013

More information

Supplementary Material Accompanying Geometry Driven Semantic Labeling of Indoor Scenes

Supplementary Material Accompanying Geometry Driven Semantic Labeling of Indoor Scenes Supplementary Material Accompanying Geometry Driven Semantic Labeling of Indoor Scenes Salman H. Khan 1, Mohammed Bennamoun 1, Ferdous Sohel 1 and Roberto Togneri 2 School of CSSE 1, School of EECE 2 The

More information

Higher-Order Energies for Image Segmentation

Higher-Order Energies for Image Segmentation IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Higher-Order Energies for Image Segmentation Jianbing Shen, Senior Member, IEEE, Jianteng Peng, Xingping Dong, Ling Shao, Senior Member, IEEE, and Fatih Porikli,

More information

Asaf Bar Zvi Adi Hayat. Semantic Segmentation

Asaf Bar Zvi Adi Hayat. Semantic Segmentation Asaf Bar Zvi Adi Hayat Semantic Segmentation Today s Topics Fully Convolutional Networks (FCN) (CVPR 2015) Conditional Random Fields as Recurrent Neural Networks (ICCV 2015) Gaussian Conditional random

More information

Course 16:198:520: Introduction To Artificial Intelligence Lecture 9. Markov Networks. Abdeslam Boularias. Monday, October 14, 2015

Course 16:198:520: Introduction To Artificial Intelligence Lecture 9. Markov Networks. Abdeslam Boularias. Monday, October 14, 2015 Course 16:198:520: Introduction To Artificial Intelligence Lecture 9 Markov Networks Abdeslam Boularias Monday, October 14, 2015 1 / 58 Overview Bayesian networks, presented in the previous lecture, are

More information

Parameter Learning for Log-supermodular Distributions

Parameter Learning for Log-supermodular Distributions Parameter Learning for Log-supermodular Distributions Tatiana Shpakova IRIA - École ormale Supérieure Paris tatiana.shpakova@inria.fr Francis Bach IRIA - École ormale Supérieure Paris francis.bach@inria.fr

More information

Structured Prediction

Structured Prediction Structured Prediction Classification Algorithms Classify objects x X into labels y Y First there was binary: Y = {0, 1} Then multiclass: Y = {1,...,6} The next generation: Structured Labels Structured

More information

A Compact Linear Programming Relaxation for Binary Sub-modular MRF

A Compact Linear Programming Relaxation for Binary Sub-modular MRF A Compact Linear Programming Relaxation for Binary Sub-modular MRF Junyan Wang and Sai-Kit Yeung Singapore University of Technology and Design {junyan_wang,saikit}@sutd.edu.sg Abstract. Direct linear programming

More information

Feedback Loop between High Level Semantics and Low Level Vision

Feedback Loop between High Level Semantics and Low Level Vision Feedback Loop between High Level Semantics and Low Level Vision Varun K. Nagaraja Vlad I. Morariu Larry S. Davis {varun,morariu,lsd}@umiacs.umd.edu University of Maryland, College Park, MD, USA. Abstract.

More information

Advanced Structured Prediction

Advanced Structured Prediction Advanced Structured Prediction Editors: Sebastian Nowozin Microsoft Research Cambridge, CB1 2FB, United Kingdom Peter V. Gehler Max Planck Insitute for Intelligent Systems 72076 Tübingen, Germany Jeremy

More information

Subproblem-Tree Calibration: A Unified Approach to Max-Product Message Passing

Subproblem-Tree Calibration: A Unified Approach to Max-Product Message Passing Subproblem-Tree Calibration: A Unified Approach to Max-Product Message Passing Huayan Wang huayanw@cs.stanford.edu Computer Science Department, Stanford University, Palo Alto, CA 90 USA Daphne Koller koller@cs.stanford.edu

More information

Modeling Mutual Context of Object and Human Pose in Human-Object Interaction Activities

Modeling Mutual Context of Object and Human Pose in Human-Object Interaction Activities Modeling Mutual Context of Object and Human Pose in Human-Object Interaction Activities Bangpeng Yao and Li Fei-Fei Computer Science Department, Stanford University {bangpeng,feifeili}@cs.stanford.edu

More information

A Graph Cut Algorithm for Generalized Image Deconvolution

A Graph Cut Algorithm for Generalized Image Deconvolution A Graph Cut Algorithm for Generalized Image Deconvolution Ashish Raj UC San Francisco San Francisco, CA 94143 Ramin Zabih Cornell University Ithaca, NY 14853 Abstract The goal of deconvolution is to recover

More information

ECE 6504: Advanced Topics in Machine Learning Probabilistic Graphical Models and Large-Scale Learning

ECE 6504: Advanced Topics in Machine Learning Probabilistic Graphical Models and Large-Scale Learning ECE 6504: Advanced Topics in Machine Learning Probabilistic Graphical Models and Large-Scale Learning Topics Summary of Class Advanced Topics Dhruv Batra Virginia Tech HW1 Grades Mean: 28.5/38 ~= 74.9%

More information

Discriminative Fields for Modeling Spatial Dependencies in Natural Images

Discriminative Fields for Modeling Spatial Dependencies in Natural Images Discriminative Fields for Modeling Spatial Dependencies in Natural Images Sanjiv Kumar and Martial Hebert The Robotics Institute Carnegie Mellon University Pittsburgh, PA 15213 {skumar,hebert}@ri.cmu.edu

More information

Pseudo-Bound Optimization for Binary Energies

Pseudo-Bound Optimization for Binary Energies In European Conference on Computer Vision (ECCV), Zurich, Switzerland, 2014 p. 1 Pseudo-Bound Optimization for Binary Energies Meng Tang 1 Ismail Ben Ayed 1,2 Yuri Boykov 1 1 University of Western Ontario,

More information

STA 4273H: Statistical Machine Learning

STA 4273H: Statistical Machine Learning STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 3 Linear

More information

Undirected Graphical Models: Markov Random Fields

Undirected Graphical Models: Markov Random Fields Undirected Graphical Models: Markov Random Fields 40-956 Advanced Topics in AI: Probabilistic Graphical Models Sharif University of Technology Soleymani Spring 2015 Markov Random Field Structure: undirected

More information

Graphical Object Models for Detection and Tracking

Graphical Object Models for Detection and Tracking Graphical Object Models for Detection and Tracking (ls@cs.brown.edu) Department of Computer Science Brown University Joined work with: -Ying Zhu, Siemens Corporate Research, Princeton, NJ -DorinComaniciu,

More information

MAP Examples. Sargur Srihari

MAP Examples. Sargur Srihari MAP Examples Sargur srihari@cedar.buffalo.edu 1 Potts Model CRF for OCR Topics Image segmentation based on energy minimization 2 Examples of MAP Many interesting examples of MAP inference are instances

More information

Notes on Markov Networks

Notes on Markov Networks Notes on Markov Networks Lili Mou moull12@sei.pku.edu.cn December, 2014 This note covers basic topics in Markov networks. We mainly talk about the formal definition, Gibbs sampling for inference, and maximum

More information

Fast Approximate Energy Minimization with Label Costs

Fast Approximate Energy Minimization with Label Costs ISBN: 978-0-7714-2823-4, Tech.Report #731, CS Dept., UWO, December 4, 2009. Revised April 25, 2010. 1 Fast Approximate Energy Minimization with Label Costs Anton Osokin Andrew Delong* * Department of Computer

More information

A Framework for Efficient Structured Max-Margin Learning of High-Order MRF Models

A Framework for Efficient Structured Max-Margin Learning of High-Order MRF Models 1 A Framework for Efficient Structured Max-Margin Learning of High-Order MRF Models Nikos Komodakis, Bo Xiang, Nikos Paragios Abstract We present a very general algorithm for structured prediction learning

More information

ECE 6504: Advanced Topics in Machine Learning Probabilistic Graphical Models and Large-Scale Learning

ECE 6504: Advanced Topics in Machine Learning Probabilistic Graphical Models and Large-Scale Learning ECE 6504: Advanced Topics in Machine Learning Probabilistic Graphical Models and Large-Scale Learning Topics Markov Random Fields: Representation Conditional Random Fields Log-Linear Models Readings: KF

More information

Quadratic Programming Relaxations for Metric Labeling and Markov Random Field MAP Estimation

Quadratic Programming Relaxations for Metric Labeling and Markov Random Field MAP Estimation Quadratic Programming Relaations for Metric Labeling and Markov Random Field MAP Estimation Pradeep Ravikumar John Lafferty School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213,

More information

A Combined LP and QP Relaxation for MAP

A Combined LP and QP Relaxation for MAP A Combined LP and QP Relaxation for MAP Patrick Pletscher ETH Zurich, Switzerland pletscher@inf.ethz.ch Sharon Wulff ETH Zurich, Switzerland sharon.wulff@inf.ethz.ch Abstract MAP inference for general

More information

Max$Sum(( Exact(Inference(

Max$Sum(( Exact(Inference( Probabilis7c( Graphical( Models( Inference( MAP( Max$Sum(( Exact(Inference( Product Summation a 1 b 1 8 a 1 b 2 1 a 2 b 1 0.5 a 2 b 2 2 a 1 b 1 3 a 1 b 2 0 a 2 b 1-1 a 2 b 2 1 Max-Sum Elimination in Chains

More information

Probabilistic Graphical Models in Computer Vision (IN2329)

Probabilistic Graphical Models in Computer Vision (IN2329) Probabilistic Graphical Models in Computer Vision (IN2329) Csaba Domokos Summer Semester 2017 11. Parameter learning............................................................................................

More information

Potts model, parametric maxflow and k-submodular functions

Potts model, parametric maxflow and k-submodular functions 2013 IEEE International Conference on Computer Vision Potts model, parametric maxflow and k-submodular functions Igor Gridchyn IST Austria igor.gridchyn@ist.ac.at Vladimir Kolmogorov IST Austria vnk@ist.ac.at

More information

Pictorial Structures Revisited: People Detection and Articulated Pose Estimation. Department of Computer Science TU Darmstadt

Pictorial Structures Revisited: People Detection and Articulated Pose Estimation. Department of Computer Science TU Darmstadt Pictorial Structures Revisited: People Detection and Articulated Pose Estimation Mykhaylo Andriluka Stefan Roth Bernt Schiele Department of Computer Science TU Darmstadt Generic model for human detection

More information

Neural networks and optimization

Neural networks and optimization Neural networks and optimization Nicolas Le Roux INRIA 8 Nov 2011 Nicolas Le Roux (INRIA) Neural networks and optimization 8 Nov 2011 1 / 80 1 Introduction 2 Linear classifier 3 Convolutional neural networks

More information

Perturb-and-MAP Random Fields: Using Discrete Optimization to Learn and Sample from Energy Models ICCV 2011 paper supplementary material

Perturb-and-MAP Random Fields: Using Discrete Optimization to Learn and Sample from Energy Models ICCV 2011 paper supplementary material Perturb-and-MAP Random Fields: Using Discrete Optimization to Learn and Sample from Energy Models ICCV 2011 paper supplementary material George Papandreou and Alan Yuille Department of Statistics, University

More information

MANY problems in computer vision, such as segmentation,

MANY problems in computer vision, such as segmentation, 134 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 33, NO. 6, JUNE 011 Transformation of General Binary MRF Minimization to the First-Order Case Hiroshi Ishikawa, Member, IEEE Abstract

More information

Part 4: Conditional Random Fields

Part 4: Conditional Random Fields Part 4: Conditional Random Fields Sebastian Nowozin and Christoph H. Lampert Colorado Springs, 25th June 2011 1 / 39 Problem (Probabilistic Learning) Let d(y x) be the (unknown) true conditional distribution.

More information

Probabilistic Graphical Models

Probabilistic Graphical Models School of Computer Science Probabilistic Graphical Models Max-margin learning of GM Eric Xing Lecture 28, Apr 28, 2014 b r a c e Reading: 1 Classical Predictive Models Input and output space: Predictive

More information

Spatial Bayesian Nonparametrics for Natural Image Segmentation

Spatial Bayesian Nonparametrics for Natural Image Segmentation Spatial Bayesian Nonparametrics for Natural Image Segmentation Erik Sudderth Brown University Joint work with Michael Jordan University of California Soumya Ghosh Brown University Parsing Visual Scenes

More information

Undirected Graphical Models

Undirected Graphical Models Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Properties Properties 3 Generative vs. Conditional

More information

Fast Memory-Efficient Generalized Belief Propagation

Fast Memory-Efficient Generalized Belief Propagation Fast Memory-Efficient Generalized Belief Propagation M. Pawan Kumar P.H.S. Torr Department of Computing Oxford Brookes University Oxford, UK, OX33 1HX {pkmudigonda,philiptorr}@brookes.ac.uk http://cms.brookes.ac.uk/computervision

More information

Computational Complexity

Computational Complexity Computational Complexity Algorithm performance and difficulty of problems So far we have seen problems admitting fast algorithms flow problems, shortest path, spanning tree... and other problems for which

More information

Optimization of Max-Norm Objective Functions in Image Processing and Computer Vision

Optimization of Max-Norm Objective Functions in Image Processing and Computer Vision Optimization of Max-Norm Objective Functions in Image Processing and Computer Vision Filip Malmberg 1, Krzysztof Chris Ciesielski 2,3, and Robin Strand 1 1 Centre for Image Analysis, Department of Information

More information

Active MAP Inference in CRFs for Efficient Semantic Segmentation

Active MAP Inference in CRFs for Efficient Semantic Segmentation 2013 IEEE International Conference on Computer Vision Active MAP Inference in CRFs for Efficient Semantic Segmentation Gemma Roig 1 Xavier Boix 1 Roderick de Nijs 2 Sebastian Ramos 3 Kolja Kühnlenz 2 Luc

More information

Statistical and Inductive Inference by Minimum Message Length

Statistical and Inductive Inference by Minimum Message Length C.S. Wallace Statistical and Inductive Inference by Minimum Message Length With 22 Figures Springer Contents Preface 1. Inductive Inference 1 1.1 Introduction 1 1.2 Inductive Inference 5 1.3 The Demise

More information

Material presented. Direct Models for Classification. Agenda. Classification. Classification (2) Classification by machines 6/16/2010.

Material presented. Direct Models for Classification. Agenda. Classification. Classification (2) Classification by machines 6/16/2010. Material presented Direct Models for Classification SCARF JHU Summer School June 18, 2010 Patrick Nguyen (panguyen@microsoft.com) What is classification? What is a linear classifier? What are Direct Models?

More information

Energy Minimization via Graph Cuts

Energy Minimization via Graph Cuts Energy Minimization via Graph Cuts Xiaowei Zhou, June 11, 2010, Journal Club Presentation 1 outline Introduction MAP formulation for vision problems Min-cut and Max-flow Problem Energy Minimization via

More information

arxiv: v1 [cs.cv] 23 Mar 2015

arxiv: v1 [cs.cv] 23 Mar 2015 Superpixelizing Binary MRF for Image Labeling Problems arxiv:1503.06642v1 [cs.cv] 23 Mar 2015 Junyan Wang and Sai-Kit Yeung Singapore University of Technology and Design, 8 Somapah Road, Singapore, 487372

More information

Parameter learning in CRF s

Parameter learning in CRF s Parameter learning in CRF s June 01, 2009 Structured output learning We ish to learn a discriminant (or compatability) function: F : X Y R (1) here X is the space of inputs and Y is the space of outputs.

More information

A Graphical Model for Simultaneous Partitioning and Labeling

A Graphical Model for Simultaneous Partitioning and Labeling A Graphical Model for Simultaneous Partitioning and Labeling Philip J Cowans Cavendish Laboratory, University of Cambridge, Cambridge, CB3 0HE, United Kingdom pjc51@camacuk Martin Szummer Microsoft Research

More information

Computational Complexity. IE 496 Lecture 6. Dr. Ted Ralphs

Computational Complexity. IE 496 Lecture 6. Dr. Ted Ralphs Computational Complexity IE 496 Lecture 6 Dr. Ted Ralphs IE496 Lecture 6 1 Reading for This Lecture N&W Sections I.5.1 and I.5.2 Wolsey Chapter 6 Kozen Lectures 21-25 IE496 Lecture 6 2 Introduction to

More information

Conditional Random Fields and beyond DANIEL KHASHABI CS 546 UIUC, 2013

Conditional Random Fields and beyond DANIEL KHASHABI CS 546 UIUC, 2013 Conditional Random Fields and beyond DANIEL KHASHABI CS 546 UIUC, 2013 Outline Modeling Inference Training Applications Outline Modeling Problem definition Discriminative vs. Generative Chain CRF General

More information

Introduction to Machine Learning Midterm, Tues April 8

Introduction to Machine Learning Midterm, Tues April 8 Introduction to Machine Learning 10-701 Midterm, Tues April 8 [1 point] Name: Andrew ID: Instructions: You are allowed a (two-sided) sheet of notes. Exam ends at 2:45pm Take a deep breath and don t spend

More information

Active Detection via Adaptive Submodularity

Active Detection via Adaptive Submodularity Active Detection via Adaptive Submodularity Yuxin Chen, Hiroaki Shioi, Cesar Antonio Fuentes Montesinos! Lian Pin Koh, Serge Wich and Andreas Krause! ICML Beijing June 23, 2014! Motivating Example: Biodiversity

More information

27 : Distributed Monte Carlo Markov Chain. 1 Recap of MCMC and Naive Parallel Gibbs Sampling

27 : Distributed Monte Carlo Markov Chain. 1 Recap of MCMC and Naive Parallel Gibbs Sampling 10-708: Probabilistic Graphical Models 10-708, Spring 2014 27 : Distributed Monte Carlo Markov Chain Lecturer: Eric P. Xing Scribes: Pengtao Xie, Khoa Luu In this scribe, we are going to review the Parallel

More information

Computing the M Most Probable Modes of a Graphical Model

Computing the M Most Probable Modes of a Graphical Model Chao Chen Vladimir Kolmogorov Yan Zhu Rutgers University IST Austria Rutgers University Dimitris Metaxas Rutgers University Christoph H. Lampert IST Austria Abstract We introduce the M-Modes problem for

More information

A new look at reweighted message passing

A new look at reweighted message passing Copyright IEEE. Accepted to Transactions on Pattern Analysis and Machine Intelligence (TPAMI) http://ieeexplore.ieee.org/xpl/articledetails.jsp?arnumber=692686 A new look at reweighted message passing

More information

Grouping with Bias. Stella X. Yu 1,2 Jianbo Shi 1. Robotics Institute 1 Carnegie Mellon University Center for the Neural Basis of Cognition 2

Grouping with Bias. Stella X. Yu 1,2 Jianbo Shi 1. Robotics Institute 1 Carnegie Mellon University Center for the Neural Basis of Cognition 2 Grouping with Bias Stella X. Yu, Jianbo Shi Robotics Institute Carnegie Mellon University Center for the Neural Basis of Cognition What Is It About? Incorporating prior knowledge into grouping Unitary

More information

Belief Propagation for Traffic forecasting

Belief Propagation for Traffic forecasting Belief Propagation for Traffic forecasting Cyril Furtlehner (INRIA Saclay - Tao team) context : Travesti project http ://travesti.gforge.inria.fr/) Anne Auger (INRIA Saclay) Dimo Brockhoff (INRIA Lille)

More information

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials by Phillip Krahenbuhl and Vladlen Koltun Presented by Adam Stambler Multi-class image segmentation Assign a class label to each

More information

Semi-Markov/Graph Cuts

Semi-Markov/Graph Cuts Semi-Markov/Graph Cuts Alireza Shafaei University of British Columbia August, 2015 1 / 30 A Quick Review For a general chain-structured UGM we have: n n p(x 1, x 2,..., x n ) φ i (x i ) φ i,i 1 (x i, x

More information

Maximum Persistency via Iterative Relaxed Inference with Graphical Models

Maximum Persistency via Iterative Relaxed Inference with Graphical Models Maximum Persistency via Iterative Relaxed Inference with Graphical Models Alexander Shekhovtsov TU Graz, Austria shekhovtsov@icg.tugraz.at Paul Swoboda Heidelberg University, Germany swoboda@math.uni-heidelberg.de

More information

A Unified View of Piecewise Linear Neural Network Verification Supplementary Materials

A Unified View of Piecewise Linear Neural Network Verification Supplementary Materials A Unified View of Piecewise Linear Neural Network Verification Supplementary Materials Rudy Bunel University of Oxford rudy@robots.ox.ac.uk Ilker Turkaslan University of Oxford ilker.turkaslan@lmh.ox.ac.uk

More information

Convex Relaxations for Markov Random Field MAP estimation

Convex Relaxations for Markov Random Field MAP estimation Convex Relaxations for Markov Random Field MAP estimation Timothee Cour GRASP Lab, University of Pennsylvania September 2008 Abstract Markov Random Fields (MRF) are commonly used in computer vision and

More information

Reformulations of nonlinear binary optimization problems

Reformulations of nonlinear binary optimization problems 1 / 36 Reformulations of nonlinear binary optimization problems Yves Crama HEC Management School, University of Liège, Belgium Koper, May 2018 2 / 36 Nonlinear 0-1 optimization Outline 1 Nonlinear 0-1

More information

Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification

Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification Sanjiv Kumar and Martial Hebert The Robotics Institute, Carnegie Mellon University Pittsburgh, PA 15213,

More information

Support Vector Machine (SVM) and Kernel Methods

Support Vector Machine (SVM) and Kernel Methods Support Vector Machine (SVM) and Kernel Methods CE-717: Machine Learning Sharif University of Technology Fall 2015 Soleymani Outline Margin concept Hard-Margin SVM Soft-Margin SVM Dual Problems of Hard-Margin

More information

Submodularity beyond submodular energies: Coupling edges in graph cuts

Submodularity beyond submodular energies: Coupling edges in graph cuts Submodularity beyond submodular energies: Coupling edges in graph cuts Stefanie Jegelka and Jeff Bilmes Max Planck Institute for Intelligent Systems Tübingen, Germany University of Washington Seattle,

More information