Normalized Cut meets MRF

Slides:



Advertisements
Similar presentations
POSE–CUT Simultaneous Segmentation and 3D Pose Estimation of Humans using Dynamic Graph Cuts Mathieu Bray Pushmeet Kohli Philip H.S. Torr Department of.
Advertisements

Mean-Field Theory and Its Applications In Computer Vision1 1.
O BJ C UT M. Pawan Kumar Philip Torr Andrew Zisserman UNIVERSITY OF OXFORD.
Generating Classic Mosaics with Graph Cuts Y. Liu, O. Veksler and O. Juan University of Western Ontario, Canada Ecole Centrale de Paris, France.
Pose Estimation and Segmentation of People in 3D Movies Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev Inria, Ecole Normale Superieure ICCV.
Spectral graph reduction for image and streaming video segmentation Fabio Galasso 1 Margret Keuper 2 Thomas Brox 2 Bernt Schiele 1 1 Max Planck Institute.
Lena Gorelick Joint work with Frank Schmidt and Yuri Boykov Rochester Institute of Technology, Center of Imaging Science January 2013 TexPoint fonts used.
Introduction to Markov Random Fields and Graph Cuts Simon Prince
Scene Labeling Using Beam Search Under Mutex Constraints ID: O-2B-6 Anirban Roy and Sinisa Todorovic Oregon State University 1.
Interactive Segmentation with Super-Labels Andrew Delong Western Yuri BoykovOlga VekslerLena GorelickFrank Schmidt TexPoint fonts used in EMF. Read the.
1School of CS&Eng The Hebrew University
The University of Ontario CS 4487/9687 Algorithms for Image Analysis Multi-Label Image Analysis Problems.
C. Olsson Higher-order and/or non-submodular optimization: Yuri Boykov jointly with Western University Canada O. Veksler Andrew Delong L. Gorelick C. NieuwenhuisE.
Stephen J. Guy 1. Photomontage Photomontage GrabCut – Interactive Foreground Extraction 1.
Graph-based image segmentation Václav Hlaváč Czech Technical University in Prague Faculty of Electrical Engineering Department of Cybernetics Prague, Czech.
GrabCut Interactive Image (and Stereo) Segmentation Joon Jae Lee Keimyung University Welcome. I will present Grabcut – an Interactive tool for foreground.
Pseudo-Bound Optimization for Binary Energies Presenter: Meng Tang Joint work with Ismail Ben AyedYuri Boykov 1 / 27.
Markov Nets Dhruv Batra, Recitation 10/30/2008.
Deformable Contours Dr. E. Ribeiro.
A Unified View of Kernel k-means, Spectral Clustering and Graph Cuts Dhillon, Inderjit S., Yuqiang Guan, and Brian Kulis.
Robust Higher Order Potentials For Enforcing Label Consistency
Image-based Shaving Eurographics Apr 2008 Minh Hoai Nguyen, Jean-Francois Lalonde, Alexei A. Efros & Fernando de la Torre Robotics Institute, Carnegie.
A Unified View of Kernel k-means, Spectral Clustering and Graph Cuts
Today: Image Segmentation Image Segmentation Techniques Snakes Scissors Graph Cuts Mean Shift Wednesday (2/28) Texture analysis and synthesis Multiple.
Improved Moves for Truncated Convex Models M. Pawan Kumar Philip Torr.
2010/5/171 Overview of graph cuts. 2010/5/172 Outline Introduction S-t Graph cuts Extension to multi-label problems Compare simulated annealing and alpha-
Graph Cut based Inference with Co-occurrence Statistics Ľubor Ladický, Chris Russell, Pushmeet Kohli, Philip Torr.
Research at Intel Distributed Localization of Modular Robot Ensembles Robotics: Science and Systems 25 June 2008 Stanislav Funiak, Michael Ashley-Rollman.
Relaxations and Moves for MAP Estimation in MRFs M. Pawan Kumar STANFORDSTANFORD Vladimir KolmogorovPhilip TorrDaphne Koller.
Image Matching via Saliency Region Correspondences Alexander Toshev Jianbo Shi Kostas Daniilidis IEEE Conference on Computer Vision and Pattern Recognition.
Measuring Uncertainty in Graph Cut Solutions Pushmeet Kohli Philip H.S. Torr Department of Computing Oxford Brookes University.
Perceptual Organization: Segmentation and Optical Flow.
Graph-based Segmentation
The Three R’s of Vision Jitendra Malik.
Graph Cut & Energy Minimization
MRFs and Segmentation with Graph Cuts Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 02/24/10.
City University of Hong Kong 18 th Intl. Conf. Pattern Recognition Self-Validated and Spatially Coherent Clustering with NS-MRF and Graph Cuts Wei Feng.
Lena Gorelick joint work with O. Veksler I. Ben Ayed A. Delong Y. Boykov.
Algorithms for MAP estimation in Markov Random Fields Vladimir Kolmogorov University College London.
1 Markov Random Fields with Efficient Approximations Yuri Boykov, Olga Veksler, Ramin Zabih Computer Science Department CORNELL UNIVERSITY.
Auxiliary Cuts for General Classes of Higher-Order Functionals 1 Ismail Ben Ayed, Lena Gorelick and Yuri Boykov.
O BJ C UT M. Pawan Kumar Philip Torr Andrew Zisserman UNIVERSITY OF OXFORD.
The University of Ontario CS 4487/9687 Algorithms for Image Analysis Multi-Label Image Analysis Problems.
Gaussian Mixture Models and Expectation-Maximization Algorithm.
Pseudo-Bound Optimization for Binary Energies Meng Tang 1 Ismail Ben Ayed 2 Yuri Boykov 1 1 University of Western Ontario, Canada 2 GE Healthcare Canada.
CS654: Digital Image Analysis Lecture 28: Advanced topics in Image Segmentation Image courtesy: IEEE, IJCV.
A global approach Finding correspondence between a pair of epipolar lines for all pixels simultaneously Local method: no guarantee we will have one to.
Optimal Reverse Prediction: Linli Xu, Martha White and Dale Schuurmans ICML 2009, Best Overall Paper Honorable Mention A Unified Perspective on Supervised,
1 Review and Summary We have covered a LOT of material, spending more time and more detail on 2D image segmentation and analysis, but hopefully giving.
Motion Segmentation at Any Speed Shrinivas J. Pundlik Department of Electrical and Computer Engineering, Clemson University, Clemson, SC.
Segmentation with non-linear constraints on appearance, complexity, and geometry Yuri Boykov Western Univesity Andrew Delong Olga Veksler Lena Gorelick.
Image segmentation.
Energy minimization Another global approach to improve quality of correspondences Assumption: disparities vary (mostly) smoothly Minimize energy function:
Document Clustering with Prior Knowledge Xiang Ji et al. Document Clustering with Prior Knowledge. SIGIR 2006 Presenter: Suhan Yu.
MRFs (X1,X2) X3 X1 X2 4 (X2,X3,X3) X4. MRFs (X1,X2) X3 X1 X2 4 (X2,X3,X3) X4.
A Closed Form Solution to Direct Motion Segmentation
Motion Segmentation with Missing Data using PowerFactorization & GPCA
Segmentation of Dynamic Scenes
Markov Random Fields with Efficient Approximations
Segmentation of Dynamic Scenes from Image Intensities
Spectral Methods Tutorial 6 1 © Maks Ovsjanikov
Secrets of GrabCut and Kernel K-means
Principal Nested Spheres Analysis
Normalized Cut Loss for Weakly-supervised CNN Segmentation
Counting in High-Density Crowd Videos
Multiway Cut for Stereo and Motion with Slanted Surfaces
Multi-view reconstruction
Spectral Clustering Eric Xing Lecture 8, August 13, 2010
Segmentation of Dynamical Scenes
“Traditional” image segmentation
Presentation transcript:

Normalized Cut meets MRF Meng Tang1 Dmitrii Marin1 Ismail Ben Ayed2 Yuri Boykov1 1University of Western Ontario, Canada 2École de Technologie Supérieure, Canada Energy Formulation Optimization: Kernel Cut and Spectral Cut Normalized Cut (NC) MRF General optimization approach: bound optimization E(S) At (S) St St+1 At+1 (S) balanced regularization unary kernel or spectral bound clustering constraints to optimize bound At(S) we use move-making graph cuts [Boykov, Veksler, Zabih, 2001] Why MRF for NC semi-supervision is challenging How to incorporate group priors? weak edge alignment How many clusters? Kernel bound for NC (exact) 8 clusters Normalized Cut is concave: NC approach: cannot-link 3 clusters Lemma (concavity) Function e : R|Ω| → R is concave over region Sk > 0 given p.s.d. affinity matrix A := [Apq]. must-link [Chew et al. 2015] [Eriksson et al. 2010] [Yu & Shi 2004] [Arbelaez et al., 2010] 1st order Taylor expansion is an upper bound for NC: at(Sk) St St+1 at+1(Sk) e(Sk) our approach: (sparsity prior) NC + label cost NC+Potts NC+Potts+seeds NC + Pn Potts MRF MRF MRF MRF Why NC for MRF (equivalently kernel k-means [Dhillon t al., 2004]) Spectral bound for NC (approx.) ML term for 𝜃 𝑘 Step 1. low-rank (m) approximation Step 2. low-dim. isomeric Euclidean embedding for SVDs Probabilistic K-means [Kearns et al., UAI’97] bad clustering (overfitting) Model Fitting (e.g. GMM) (GrabCut without smoothness) Normalized Cut good clustering and low-rank m implying isometry MDS [Cox & Cox., 2000] Kernel PCA [Schölkopf et al., 1998] NC K-means unary spectral bound Summary of contribution new unary kernel and spectral bounds for NC can combine NC with any MRF constraints can combine MRF with balanced clustering MRF with features of any dimension (RGBD, RGBM, RGBXYM, deep,…) We show NC ≈ K-means via low-rank (m) approximation In contrast, K-means is a discretization heuristic in NC spectral relaxation [Shi & Malik 2000, Yu & Shi 2003] Spectral bound accuracy (depending on m) m = 3 K-means m = 10 NC Experiments: NC helps MRF Experiments: MRF helps NC poor scalability to high-dim GrabCut Kernel Cut Potts model improves edge alignment RGBD segmentation BSDS500 measure Covering PRI VOI Spectral Clustering 0.34 0.76 2.76 Our Kernel Cut 0.41 0.78 2.44 Our Spectral Cut 0.42 2.34 Spectral Clustering (no Potts) Our Kernel Cut (NC with Potts) Our Spectral Cut (NC with Potts) High dimension feature : RGBXYM (location XY, motion M) Label cost Robust Pn Potts using image tags (e.g. beach, car) to help clustering Image clustering with tags consistency prior Our Kernel Cut with increasing label cost (a)Video frames (b)Optical flow (c)Kernel Cut(RGBXY) (d)Kernel Cut(RGBXYM)