Optimal invariant metrics for shape retrieval

Slides:



Advertisements
Similar presentations
Ter Haar Romeny, ICPR 2010 Introduction to Scale-Space and Deep Structure.
Advertisements

Distinctive Image Features from Scale-Invariant Keypoints David Lowe.
Aggregating local image descriptors into compact codes
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
Three things everyone should know to improve object retrieval
MIT CSAIL Vision interfaces Towards efficient matching with random hashing methods… Kristen Grauman Gregory Shakhnarovich Trevor Darrell.
Classification using intersection kernel SVMs is efficient Joint work with Subhransu Maji and Alex Berg Jitendra Malik UC Berkeley.
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
1 Michael Bronstein Heat diffusion descriptors deformable Michael Bronstein Weizmann Institute of Science, 4 November 2010 Institute of Computational Science.
1 Overview of Image Retrieval Hui-Ying Wang. 2/42 Reference Smeulders, A. W., Worring, M., Santini, S., Gupta, A.,, and Jain, R “Content-based.
Persistent Heat Signature for Pose-oblivious Matching of Incomplete Models Tamal K. Dey, Kuiyu Li, Chuanjiang Luo, Pawas Ranjan, Issam Safa, Yusu Wang.
1 Numerical Geometry of Non-Rigid Shapes Diffusion Geometry Diffusion geometry © Alexander & Michael Bronstein, © Michael Bronstein, 2010 tosca.cs.technion.ac.il/book.
Probabilistic Fingerprints for Shapes Niloy J. MitraLeonidas Guibas Joachim GiesenMark Pauly Stanford University MPII SaarbrückenETH Zurich.
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Discriminative and generative methods for bags of features
Fast High-Dimensional Feature Matching for Object Recognition David Lowe Computer Science Department University of British Columbia.
Content Based Image Clustering and Image Retrieval Using Multiple Instance Learning Using Multiple Instance Learning Xin Chen Advisor: Chengcui Zhang Department.
1 Numerical Geometry of Non-Rigid Shapes Feature-based methods & shape retrieval problems Feature-based methods and shape retrieval problems © Alexander.
1 Michael Bronstein Shapes as metric spaces: deformation-invariant similarity Michael Bronstein Computational metric geometry: an old new tool in image.
1 Michael Bronstein Computational metric geometry Computational metric geometry Michael Bronstein Department of Computer Science Technion – Israel Institute.
An Optimization Approach to Improving Collections of Shape Maps Andy Nguyen, Mirela Ben-Chen, Katarzyna Welnicka, Yinyu Ye, Leonidas Guibas Computer Science.
Small Codes and Large Image Databases for Recognition CVPR 2008 Antonio Torralba, MIT Rob Fergus, NYU Yair Weiss, Hebrew University.
Algorithms and Applications in Computer Vision
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
Iterative closest point algorithms
1 Bronstein 2 and Kimmel Extrinsic and intrinsic similarity of nonrigid shapes Michael M. Bronstein Department of Computer Science Technion – Israel Institute.
1 Jun Wang, 2 Sanjiv Kumar, and 1 Shih-Fu Chang 1 Columbia University, New York, USA 2 Google Research, New York, USA Sequential Projection Learning for.
Correspondence & Symmetry
1 Numerical geometry of non-rigid shapes Spectral Methods Tutorial. Spectral Methods Tutorial 6 © Maks Ovsjanikov tosca.cs.technion.ac.il/book Numerical.
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and.
Feature-based methods
Similarity Search in High Dimensions via Hashing Aristides Gionis, Protr Indyk and Rajeev Motwani Department of Computer Science Stanford University presented.
Numerical geometry of non-rigid shapes
1 Bronstein, Bronstein, and Kimmel Joint extrinsic and intrinsic similarity of non-rigid shapes Rock, paper, and scissors Joint extrinsic and intrinsic.
Scale Invariant Feature Transform (SIFT)
Paretian similarity for partial comparison of non-rigid objects
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2006 with a lot of slides stolen from Steve Seitz and.
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
1 Michael M. Bronstein Partial similarity of objects 17 December 2006 Partial similarity of objects, or how to compare a centaur to a horse Michael M.
Distinctive Image Features from Scale-Invariant Keypoints David G. Lowe – IJCV 2004 Brien Flewelling CPSC 643 Presentation 1.
Lecture 6: Feature matching and alignment CS4670: Computer Vision Noah Snavely.
Large Scale Recognition and Retrieval. What does the world look like? High level image statistics Object Recognition for large-scale search Focus on scaling.
TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: AA A A A AA A A A A A A A A  Justin Solomon,
Internet-scale Imagery for Graphics and Vision James Hays cs195g Computational Photography Brown University, Spring 2010.
1 Faculty of Information Technology Generic Fourier Descriptor for Shape-based Image Retrieval Dengsheng Zhang, Guojun Lu Gippsland School of Comp. & Info.
Bag of Visual Words for Image Representation & Visual Search Jianping Fan Dept of Computer Science UNC-Charlotte.
Shape Matching for Model Alignment 3D Scan Matching and Registration, Part I ICCV 2005 Short Course Michael Kazhdan Johns Hopkins University.
Top-points in Image Matching Bram Platel Evgenya Balmashnova Luc Florack Bart ter Haar Romeny.
A Statistical Approach to Speed Up Ranking/Re-Ranking Hong-Ming Chen Advisor: Professor Shih-Fu Chang.
Spectral Global Intrinsic Symmetry Invariant Functions Hui Wang Shijiazhuang Tiedao University Patricio Simari The Catholic University of America Zhixun.
Classifiers Given a feature representation for images, how do we learn a model for distinguishing features from different classes? Zebra Non-zebra Decision.
Beyond Sliding Windows: Object Localization by Efficient Subwindow Search The best paper prize at CVPR 2008.
Roee Litman, Alexander Bronstein, Michael Bronstein
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
Visual Categorization With Bags of Keypoints Original Authors: G. Csurka, C.R. Dance, L. Fan, J. Willamowski, C. Bray ECCV Workshop on Statistical Learning.
Harris Corner Detector & Scale Invariant Feature Transform (SIFT)
Department of Computer Science Center for Visual Computing Bag-of-Feature-Graphs: A New Paradigm for Non-rigid Shape Retrieval Tingbo HOU, Xiaohua HOU,
Distinctive Image Features from Scale-Invariant Keypoints
Introduction to Scale Space and Deep Structure. Importance of Scale Painting by Dali Objects exist at certain ranges of scale. It is not known a priory.
1 Faculty of Information Technology Enhanced Generic Fourier Descriptor for Object-Based Image Retrieval Dengsheng Zhang, Guojun Lu Gippsland School of.
Finding Clusters within a Class to Improve Classification Accuracy Literature Survey Yong Jae Lee 3/6/08.
Cross-modal Hashing Through Ranking Subspace Learning
KNN & Naïve Bayes Hongning Wang
Comparison with Counterparts
CS262: Computer Vision Lect 09: SIFT Descriptors
Scale Invariant Feature Transform (SIFT)
Web Data Integration Using Approximate String Join
Spectral Methods Tutorial 6 1 © Maks Ovsjanikov
Rob Fergus Computer Vision
Presentation transcript:

Optimal invariant metrics for shape retrieval Michael Bronstein Department of Computer Science Technion – Israel Institute of Technology TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: A 1

Text search Tagged shapes Content-based search Shapes without metadata 3D warehouse Text search Person Man, person, human Tagged shapes Content-based search Shapes without metadata

Outline ? Feature descriptor Geometric words Bag of words

Invariance Rigid Scale Inelastic Topology Local geodesic distance histogram Gaussian curvature Heat kernel signature (HKS) Scale-invariant HKS (SI-HKS) Wang, B 2010

Heat kernels Heat equation governs heat propagation on a surface Initial conditions: heat distribution at time Solution : heat distribution at time Heat kernel is a fundamental solution of the heat equation with point heat source at (heat value at point after time )

Heat kernel signature can be interpreted as probability of Brownian motion to return to the same point after time (represents “stability” of the point) Multiscale local shape descriptor Time (scale) Sun, Ovsjanikov & Guibas SGP 2009 7

Heat kernel signatures represented in RGB space Sun, Ovsjanikov, Guibas SGP 2009 Ovsjanikov, BB & Guibas NORDIA 2009 8

Scale invariance Original shape Scaled by HKS= HKS= Not scale invariant! B, Kokkinos CVPR 2010

Scaling = shift and multiplicative constant in HKS Scale-invariant heat kernel signature Log scale-space log + d/d Fourier transform magnitude 100 200 300 -15 -10 -5 t 100 200 300 -0.04 -0.03 -0.02 -0.01 t 2 4 6 8 10 12 14 16 18 20 1 3 =2k/T Scaling = shift and multiplicative constant in HKS Undo scaling Undo shift B, Kokkinos CVPR 2010

Scale invariance Heat Kernel Signature Scale-invariant B, Kokkinos CVPR 2010

Scale invariance Heat Kernel Signature Scale-invariant B, Kokkinos CVPR 2010

Modeling vs learning Wang, B 2010 13

Learning invariance T Positives P Negatives N

Similarity learning positive false positive negative false negative with high probability 15

Similarity-preserving hashing -1 -1 +1 -1 -1 -1 -1 +1 -1 -1 +1 +1 = # of distinct bits +1 +1 -1 +1 +1 +1 +1 -1 +1 +1 +1 +1 Collision: with high probability with low probability Gionis, Indik, Motwani 1999 Shakhnarovich 2005 16

Boosting -1 +1 Construct 1D embedding Similarity is approximated by Downweight pairs with Upweight pairs with BBK 2010; BB Ovsjanikov, Guibas 2010 Shakhnarovich 2005 17

Boosting -1 -1 -1 +1 +1 -1 -1 +1 +1 +1 Construct 1D embedding Similarity is approximated by +1 +1 Downweight pairs with Upweight pairs with BBK 2010; BB Ovsjanikov, Guibas 2010 Shakhnarovich 2005 18

SHREC 2010 dataset 19

Total dataset size: 1K shapes (715 queries) Positives: 10K Negatives: 100K BB et al, 3DOR 2010 SHREC 2010 dataset 20

ShapeGoogle with HKS descriptor BB et al, 3DOR 2010 ShapeGoogle with HKS descriptor 21

ShapeGoogle with SI-HKS descriptor BB et al, 3DOR 2010 ShapeGoogle with SI-HKS descriptor 22

Similarity sensitive hashing (96 bit) BB et al, 3DOR 2010 Similarity sensitive hashing (96 bit) 23

WaldHash Construct embedding by maximizing positive Early decision negative Remove pairs with and sample in new pairs into the training set Downweight pairs with Upweight pairs with B2, Ovsjanikov, Guibas 2010 24

30% B2, Ovsjanikov, Guibas 2010 25

Incommensurable spaces! How to compare apples to oranges? Cross-modal similarity Modality 1 Modality 2 Incommensurable spaces! Objects belonging to different modalities usually have different dimensionality and structure and are generated by different processes. Comparing such data is like comparing apples to oranges. Triangular meshes Point clouds How to compare apples to oranges? BB, Michel, Paragios CVPR 2010

Cross-modality embedding The key idea of our paper is to embed incommensurable data into a common metric space, in such a way that positive pairs are mapped to nearby points, while negative pairs are mapped to far away points in the embedding space. BB, Michel, Paragios CVPR 2010 with high probability

Cross-modality hashing -1 -1 +1 -1 -1 -1 -1 +1 -1 -1 +1 +1 +1 +1 -1 +1 +1 +1 +1 -1 +1 -1 -1 +1 The key idea of our paper is to embed incommensurable data into a common metric space, in such a way that positive pairs are mapped to nearby points, while negative pairs are mapped to far away points in the embedding space. Collision: with high probability with low probability BB, Michel, Paragios CVPR 2010

Cross-representation 3D shape retrieval Database Query 1052 shapes In first example application of our generic approach, we tried to retrieve three dimensional shapes with the query and the database represented using different descriptors. 8x8 dimensional bag of expressions 32-dimensional bag of words BB, Michel, Paragios CVPR 2010

Mean average precision Retrieval performance Mean average precision Our cross-modality metric outperforms Euclidean distances applied to each modality independently. It is only slightly inferior to optimal uni-modal metrics. BB, Michel, Paragios CVPR 2010 Number of bits