Ziming Zhang *, Ze-Nian Li, Mark Drew School of Computing Science, Simon Fraser University, Vancouver, B.C., Canada {zza27, li, Learning.

Slides:



Advertisements
Similar presentations
Improving the Fisher Kernel for Large-Scale Image Classification Florent Perronnin, Jorge Sanchez, and Thomas Mensink, ECCV 2010 VGG reading group, January.
Advertisements

Context-based object-class recognition and retrieval by generalized correlograms by J. Amores, N. Sebe and P. Radeva Discussion led by Qi An Duke University.
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
Foreground Focus: Finding Meaningful Features in Unlabeled Images Yong Jae Lee and Kristen Grauman University of Texas at Austin.
Olivier Duchenne , Armand Joulin , Jean Ponce Willow Lab , ICCV2011.
Clustering with k-means and mixture of Gaussian densities Jakob Verbeek December 3, 2010 Course website:
Multi-layer Orthogonal Codebook for Image Classification Presented by Xia Li.
MIT CSAIL Vision interfaces Approximate Correspondences in High Dimensions Kristen Grauman* Trevor Darrell MIT CSAIL (*) UT Austin…
CS395: Visual Recognition Spatial Pyramid Matching Heath Vinicombe The University of Texas at Austin 21 st September 2012.
1 Part 1: Classical Image Classification Methods Kai Yu Dept. of Media Analytics NEC Laboratories America Andrew Ng Computer Science Dept. Stanford University.
Detecting Categories in News Video Using Image Features Slav Petrov, Arlo Faria, Pascal Michaillat, Alex Berg, Andreas Stolcke, Dan Klein, Jitendra Malik.
Intelligent Systems Lab. Recognizing Human actions from Still Images with Latent Poses Authors: Weilong Yang, Yang Wang, and Greg Mori Simon Fraser University,
Ziming Zhang*, Ze-Nian Li, Mark Drew School of Computing Science Simon Fraser University Vancouver, Canada {zza27, li, AdaMKL: A Novel.
Global spatial layout: spatial pyramid matching Spatial weighting the features Beyond bags of features: Adding spatial information.
Discriminative and generative methods for bags of features
We propose a successive convex matching method to detect actions in videos. The proposed scheme does not need foreground/background separation, works in.
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
A Study of Approaches for Object Recognition
1 Unsupervised Modeling and Recognition of Object Categories with Combination of Visual Contents and Geometric Similarity Links Gunhee Kim Christos Faloutsos.
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
1 Diffusion Distance for Histogram Comparison, CVPR06. Haibin Ling, Kazunori Okada Group Meeting Presented by Wyman 3/14/2006.
Local Features and Kernels for Classification of Object Categories J. Zhang --- QMUL UK (INRIA till July 2005) with M. Marszalek and C. Schmid --- INRIA.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
Discriminative and generative methods for bags of features
A String Matching Approach for Visual Retrieval and Classification Mei-Chen Yeh* and Kwang-Ting Cheng Learning-Based Multimedia Lab Department of Electrical.
Large Scale Recognition and Retrieval. What does the world look like? High level image statistics Object Recognition for large-scale search Focus on scaling.
Review: Intro to recognition Recognition tasks Machine learning approach: training, testing, generalization Example classifiers Nearest neighbor Linear.
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Step 3: Classification Learn a decision rule (classifier) assigning bag-of-features representations of images to different classes Decision boundary Zebra.
A Thousand Words in a Scene P. Quelhas, F. Monay, J. Odobez, D. Gatica-Perez and T. Tuytelaars PAMI, Sept
Classification 2: discriminative models
Problem Statement A pair of images or videos in which one is close to the exact duplicate of the other, but different in conditions related to capture,
Marcin Marszałek, Ivan Laptev, Cordelia Schmid Computer Vision and Pattern Recognition, CVPR Actions in Context.
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Svetlana Lazebnik, Cordelia Schmid, Jean Ponce
Yao, B., and Fei-fei, L. IEEE Transactions on PAMI(2012)
SVM-KNN Discriminative Nearest Neighbor Classification for Visual Category Recognition Hao Zhang, Alex Berg, Michael Maire, Jitendra Malik.
Classifying Images with Visual/Textual Cues By Steven Kappes and Yan Cao.
Representations for object class recognition David Lowe Department of Computer Science University of British Columbia Vancouver, Canada Sept. 21, 2006.
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.
Efficient Subwindow Search: A Branch and Bound Framework for Object Localization ‘PAMI09 Beyond Sliding Windows: Object Localization by Efficient Subwindow.
In Defense of Nearest-Neighbor Based Image Classification Oren Boiman The Weizmann Institute of Science Rehovot, ISRAEL Eli Shechtman Adobe Systems Inc.
Locality-constrained Linear Coding for Image Classification
Visual Categorization With Bags of Keypoints Original Authors: G. Csurka, C.R. Dance, L. Fan, J. Willamowski, C. Bray ECCV Workshop on Statistical Learning.
Methods for classification and image representation
Grouplet: A Structured Image Representation for Recognizing Human and Object Interactions Bangpeng Yao and Li Fei-Fei Computer Science Department, Stanford.
Hierarchical Matching with Side Information for Image Classification
CS 1699: Intro to Computer Vision Support Vector Machines Prof. Adriana Kovashka University of Pittsburgh October 29, 2015.
First-Person Activity Recognition: What Are They Doing to Me? M. S. Ryoo and Larry Matthies Jet Propulsion Laboratory, California Institute of Technology,
Guest lecture: Feature Selection Alan Qi Dec 2, 2004.
A Theoretical Analysis of Feature Pooling in Visual Recognition Y-Lan Boureau, Jean Ponce and Yann LeCun ICML 2010 Presented by Bo Chen.
Goggle Gist on the Google Phone A Content-based image retrieval system for the Google phone Manu Viswanathan Chin-Kai Chang Ji Hyun Moon.
SUN Database: Large-scale Scene Recognition from Abbey to Zoo Jianxiong Xiao *James Haysy Krista A. Ehinger Aude Oliva Antonio Torralba Massachusetts Institute.
A Binary Linear Programming Formulation of the Graph Edit Distance Presented by Shihao Ji Duke University Machine Learning Group July 17, 2006 Authors:
Finding Clusters within a Class to Improve Classification Accuracy Literature Survey Yong Jae Lee 3/6/08.
NICTA SML Seminar, May 26, 2011 Modeling spatial layout for image classification Jakob Verbeek 1 Joint work with Josip Krapac 1 & Frédéric Jurie 2 1: LEAR.
Lecture IX: Object Recognition (2)
Learning Mid-Level Features For Recognition
Recognizing Deformable Shapes
Nonparametric Semantic Segmentation
Paper Presentation: Shape and Matching
ICCV Hierarchical Part Matching for Fine-Grained Image Classification
Digit Recognition using SVMS
IEEE ICIP Feature Normalization for Part-Based Image Classification
CVPR 2014 Orientational Pyramid Matching for Recognizing Indoor Scenes
Multiple Feature Learning for Action Classification
A Graph-Matching Kernel for Object Categorization
Boris Babenko, Steve Branson, Serge Belongie
Presentation transcript:

Ziming Zhang *, Ze-Nian Li, Mark Drew School of Computing Science, Simon Fraser University, Vancouver, B.C., Canada {zza27, li, Learning Image Similarities via Probabilistic Feature Matching 1 *This work was done when the author was in SFU.

Outline 2 Introduction Probabilistic-matching based similarity learning Probabilistic feature matching function Probabilistic feature matching learning Experiments Conclusion

Introduction 3 Object-based image similarity Ideally two images are supposed to have a higher similarity if they contain similar objects. Feature matching A natural way to measure the image similarities Many different criteria In this talk, we simply match features only based on their appearance information

4 >

Introduction 5 Several relevant feature matching approaches Summation kernel Max-selection kernel Optimal assignment kernel

Introduction 6

7 Our approach is a generalization of a family of SIMILARITY learning approaches, including the three above. Similarity matrix ≠ Kernel A kernel matrix can be considered as a special similarity matrix (i.e. symmetric positive semi-definite) Classification with Support Vector Machines (SVM)

Probabilistic-matching based similarity learning 8 How to learn these feature matching probabilities?

Feature Matching Function 9 Given two images X={x 1,…,x |X| } and Y={y 1,…,y |Y| }, a feature matching function α can be defined as Explanations of matching processes in the Summation Kernel, Max-selection Kernel, and Optimal Assignment Kernel using feature matching functions K sum : K max : K OA :

Probabilistic Feature Matching Function 10 Our probabilistic feature matching function α is defined in the vector space covered by the following convex set: Total matching probability of one feature Total matching probability of all features Each matching probability

Probabilistic Feature Matching Learning 11 Data-dependent optimization Image similarity Distribution sparseness (or Regulizer)

Probabilistic Feature Matching Learning 12 Theorems Consider max f(x) over x X, where f(x) is convex, and X is a closed convex set. If the optimum exists, a boundary point of X is the optimum. If a convex function f(x) attains its maximum on a convex polyhedron X with some extreme points, then this maximum is attained at an extreme point of X. Relation to K sum, K max, and K OA K sum : C=+∞ and H={i,j} K max : C=0 and H={i}, and C=0 and H={j} K OA : C=0 and H={i,j}

Probabilistic Feature Matching Learning 13 Proposition For two images X and Y, both the sparseness of α and their similarity will decrease monotonically with increasing the parameter C.

Probabilistic Feature Matching Learning 14

Experiments 15 Datasets: Graz Descriptor SIFT + dense sampling Image Representation 3*3 spatial Bag-of-Word histograms with 200 codewords Feature similarity: RBF- kernel with χ 2 distance 50 runs Graz-01 Graz-02

Experiments 16 Graz-01 (a) PFM 1 with H={i,j} (b) PFM 2 with H={i} or H={j} (c) PFM 3 with H= ф

Experiments 17 BikePersonAverage SPK [1] 86.3± ± PDK [2] 90.2± ± PFM 1 (C=0)90.6± ± PFM 2 (C=5)89.6± ± PFM 3 (C=+∞)89.6± ± Table 1. Comparison results between different approaches on Graz-01 (%) [1] Lazebnik et. al., “Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories,” in CVPR’06. [2] Ling and Soatto, “Proximity distribution kernels for geometric context in category recognition,” in ICCV’07.

Experiments 18 Graz-02 (a) PFM 1 with H={i,j}(b) PFM 2 with H={i} or H={j} (c) PFM 3 with H= ф

Experiments 19 BikePersonCarAverage Boost.+SIFT [3] Boost.+comb. [3] PDK+SIFT [2] PDK+hybrid [2] PFM 1 +SIFT (C=5) PFM 1 +SIFT (C=10) PFM 1 +SIFT (C=+∞) Table 2. Comparison results between different approaches on Graz-02 (%) Opelt et. al., “Generic object recognition with boosting,” PAMI, 2006.

Conclusion 20 Probabilistic feature matching scheme A generalization of a rich family of probabilistic feature matching approaches Easy to control the sparseness of the matching probability distributions and their corresponding image similarities

21 Thank you !!!