Image Parsing: Unifying Segmentation and Detection Z. Tu, X. Chen, A.L. Yuille and S-C. Hz ICCV 2003 (Marr Prize) & IJCV 2005 Sanketh Shetty.

Slides:



Advertisements
Similar presentations
Complex Networks for Representation and Characterization of Images For CS790g Project Bingdong Li 9/23/2009.
Advertisements

1 Image Parsing: Unifying Segmentation, Detection, and Recognition Shai Bagon Oren Boiman.
Agenda Introduction Bag-of-words models Visual words with spatial location Part-based models Discriminative methods Segmentation and recognition Recognition-based.
Bayesian Estimation in MARK
Pulsar Detection and Parameter Estimation with MCMC - Six Parameters Nelson Christensen Physics and Astronomy Carleton College GWDAW December 2003.
Introduction of Markov Chain Monte Carlo Jeongkyun Lee.
Ch 11. Sampling Models Pattern Recognition and Machine Learning, C. M. Bishop, Summarized by I.-H. Lee Biointelligence Laboratory, Seoul National.
Learning to estimate human pose with data driven belief propagation Gang Hua, Ming-Hsuan Yang, Ying Wu CVPR 05.
Mixture of trees model: Face Detection, Pose Estimation and Landmark Localization Presenter: Zhang Li.
Computer Vision Lab. SNU Young Ki Baik An Introduction to MCMC for Machine Learning (Markov Chain Monte Carlo)
Proportion Priors for Image Sequence Segmentation Claudia Nieuwenhuis, etc. ICCV 2013 Oral.
Qualifying Exam: Contour Grouping Vida Movahedi Supervisor: James Elder Supervisory Committee: Minas Spetsakis, Jeff Edmonds York University Summer 2009.
LOCUS (Learning Object Classes with Unsupervised Segmentation) A variational approach to learning model- based segmentation. John Winn Microsoft Research.
EE462 MLCV Lecture Introduction of Graphical Models Markov Random Fields Segmentation Tae-Kyun Kim 1.
Ghunhui Gu, Joseph J. Lim, Pablo Arbeláez, Jitendra Malik University of California at Berkeley Berkeley, CA
Introduction to Sampling based inference and MCMC Ata Kaban School of Computer Science The University of Birmingham.
10/11/2001Random walks and spectral segmentation1 CSE 291 Fall 2001 Marina Meila and Jianbo Shi: Learning Segmentation by Random Walks/A Random Walks View.
Stochastic approximate inference Kay H. Brodersen Computational Neuroeconomics Group Department of Economics University of Zurich Machine Learning and.
BAYESIAN INFERENCE Sampling techniques
Edge Detection Enhancement Using Gibbs Sampler
1 CE 530 Molecular Simulation Lecture 8 Markov Processes David A. Kofke Department of Chemical Engineering SUNY Buffalo
1 Hierarchical Image-Motion Segmentation using Swendsen-Wang Cuts Adrian Barbu Siemens Corporate Research Princeton, NJ Acknowledgements: S.C. Zhu, Y.N.
Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes (CVPR’10) Shengcai Liao, Guoying Zhao, Vili Kellokumpu,
Segmentation. Terminology Segmentation, grouping, perceptual organization: gathering features that belong together Fitting: associating a model with observed.
Segmentation and Tracking of Multiple Humans in Crowded Environments Tao Zhao, Ram Nevatia, Bo Wu IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,
A Study of Approaches for Object Recognition
Today Introduction to MCMC Particle filters and MCMC
Bayesian Analysis for Extreme Events Pao-Shin Chu and Xin Zhao Department of Meteorology School of Ocean & Earth Science & Technology University of Hawaii-
Computer Vision Segmentation Marc Pollefeys COMP 256 Some slides and illustrations from D. Forsyth, T. Darrel,...
Data-Driven Markov Chain Monte Carlo Presented by Tomasz MalisiewiczTomasz Malisiewicz for Advanced PerceptionAdvanced Perception 3/1/2006.
Approximate Inference 2: Monte Carlo Markov Chain
6. Markov Chain. State Space The state space is the set of values a random variable X can take. E.g.: integer 1 to 6 in a dice experiment, or the locations.
Bayes Factor Based on Han and Carlin (2001, JASA).
Learning Based Hierarchical Vessel Segmentation
SPIE'01CIRL-JHU1 Dynamic Composition of Tracking Primitives for Interactive Vision-Guided Navigation D. Burschka and G. Hager Computational Interaction.
A General Framework for Tracking Multiple People from a Moving Camera
Recognition using Regions (Demo) Sudheendra V. Outline Generating multiple segmentations –Normalized cuts [Ren & Malik (2003)] Uniform regions –Watershed.
Jifeng Dai 2011/09/27.  Introduction  Structural SVM  Kernel Design  Segmentation and parameter learning  Object Feature Descriptors  Experimental.
Leo Zhu CSAIL MIT Joint work with Chen, Yuille, Freeman and Torralba 1.
Supervised Learning of Edges and Object Boundaries Piotr Dollár Zhuowen Tu Serge Belongie.
Markov Random Fields Probabilistic Models for Images
Suppressing Random Walks in Markov Chain Monte Carlo Using Ordered Overrelaxation Radford M. Neal 발표자 : 장 정 호.
Markov-Chain Monte Carlo CSE586 Computer Vision II Spring 2010, Penn State Univ.
MTA SzTAKI & Veszprém University (Hungary) Guests at INRIA, Sophia Antipolis, 2000 and 2001 Paintbrush Rendering of Images Tamás Szirányi.
Bayesian Reasoning: Tempering & Sampling A/Prof Geraint F. Lewis Rm 560:
1 Tree Crown Extraction Using Marked Point Processes Guillaume Perrin Xavier Descombes – Josiane Zerubia ARIANA, joint research group CNRS/INRIA/UNSA INRIA.
Inference in generative models of images and video John Winn MSR Cambridge May 2004.
An Introduction to Markov Chain Monte Carlo Teg Grenager July 1, 2004.
Lecture #9: Introduction to Markov Chain Monte Carlo, part 3
Reducing MCMC Computational Cost With a Two Layered Bayesian Approach
Ch.8 Efficient Coding of Visual Scenes by Grouping and Segmentation Bayesian Brain Tai Sing Lee and Alan L. Yuille Heo, Min-Oh.
CSE 185 Introduction to Computer Vision Feature Matching.
Towards Total Scene Understanding: Classification, Annotation and Segmentation in an Automatic Framework N 工科所 錢雅馨 2011/01/16 Li-Jia Li, Richard.
Segmentation Through Optimization Pyry Matikainen.
Introduction to Sampling Methods Qi Zhao Oct.27,2004.
The Unscented Particle Filter 2000/09/29 이 시은. Introduction Filtering –estimate the states(parameters or hidden variable) as a set of observations becomes.
CS Statistical Machine learning Lecture 25 Yuan (Alan) Qi Purdue CS Nov
Bayesian Modelling Harry R. Erwin, PhD School of Computing and Technology University of Sunderland.
Representation in Vision Derek Hoiem CS 598, Spring 2009 Jan 22, 2009.
Bayesian Inference and Visual Processing: Image Parsing & DDMCMC. Alan Yuille (Dept. Statistics. UCLA) Tu, Chen, Yuille & Zhu (ICCV 2003).
Introduction to Sampling based inference and MCMC
MCMC Output & Metropolis-Hastings Algorithm Part I
Advanced Statistical Computing Fall 2016
Simple Instances of Swendson-Wang & RJMCMC
Data-Driven Markov Chain Monte Carlo
Outline Image Segmentation by Data-Driven Markov Chain Monte Carlo
Edges/curves /blobs Grammars are important because:
Integration and Graphical Models
Image Parsing & DDMCMC. Alan Yuille (Dept. Statistics. UCLA)
Markov Networks.
Presentation transcript:

Image Parsing: Unifying Segmentation and Detection Z. Tu, X. Chen, A.L. Yuille and S-C. Hz ICCV 2003 (Marr Prize) & IJCV 2005 Sanketh Shetty

Outline Why Image Parsing? Introduction to Concepts in DDMCMC DDMCMC applied to Image Parsing Combining Discriminative and Generative Models for Parsing Results Comments

Image Parsing Image I Parse Structure W Optimize p(W|I)

Properties of Parse Structure Dynamic and reconfigurable –Variable number of nodes and node types Defined by a Markov Chain –Data Driven Markov Chain Monte Carlo (earlier work in segmentation, grouping and recognition)

Key Concepts Joint model for Segmentation & Recognition –Combine different modules to obtain cues Fully generative explanation for Image generation –Uses Generative and Discriminative Models + DDMCMC framework –Concurrent Top-Down & Bottom-Up Parsing

Pattern Classes 62 characters Faces Regions

Key Concepts: –Markov Chains –Markov Chain Monte Carlo Metropolis-Hastings [Metropolis 1953, Hastings 1970] Reversible Jump [Green 1995] –Data Driven Markov Chain Monte Carlo MCMC: A Quick Tour

Markov Chains Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005

Markov Chain Monte Carlo Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005

Metropolis-Hastings Algorithm Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005

Metropolis-Hastings Algorithm Proposal Distribution Invariant Distribution Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005

Reversible Jumps MCMC Many competing models to explain data –Need to explore this complicated state space Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005

DDMCMC Motivation Notes: Slides by Zhu, Dellaert and Tu at ICCV 2005

DDMCMC Motivation Generative Model p(I|W)p(W) State Space

DDMCMC Motivation Generative Model p(I|W)p(W) State Space Discriminative Model q( w j | I ) Dramatically reduce search space by focusing sampling to highly probable states.

DDMCMC Framework Moves: –Node Creation –Node Deletion –Change Node Attributes

Transition Kernel Satisfies detailed balanced equation Full Transition Kernel

Convergence to p(W|I) Monotonically at a geometric rate

Criteria for Designing Transition Kernels

Image Generation Model Regions: Constant Intensity Textures Shading State of parse graph

62 characters Faces 3 Regions

Uniform Designed to penalize high model complexity

Shape Prior Faces 3 Regions

Shape Prior: Text

Intensity Models

Intensity Model: Faces

Discriminative Cues Used Adaboost Trained –Face Detector –Text Detector Adaptive Binarization Cues Edge Cues –Canny at 3 scales Shape Affinity Cues Region Affinity Cues

Transition Kernel Design Remember

Possible Transitions 1.Birth/Death of a Face Node 2.Birth/Death of Text Node 3.Boundary Evolution 4.Split/Merge Region 5.Change node attributes

Face/Text Transitions

Region Transitions

Change Node Attributes

Basic Control Algorithm

Results

Comments Well motivated but very complicated approach to THE HOLY GRAIL problem in vision –Good global convergence results for inference with very minor dependence on initial W. –Extensible to larger set of primitives and pattern types. Many details of the algorithm are missing and it is hard to understand the motivation for choices of values for some parameters Unclear if the p(W|I)’s for configurations with different class compositions are comparable. Derek’s comment on Adaboost false positives and their failure to report their exact improvement No quantitative results/comparison to other algorithms and approaches –It should be possible to design a simple experiment to measure performance on recognition/detection/localization tasks.

Thank You