Unsupervised Detection of Regions of Interest Using Iterative Link Analysis Gunhee Kim 1 Antonio Torralba 2 1: SCS, CMU 2: CSAIL, MIT Neural Information.

Slides:



Advertisements
Similar presentations
Location Recognition Given: A query image A database of images with known locations Two types of approaches: Direct matching: directly match image features.
Advertisements

Unsupervised Learning Clustering K-Means. Recall: Key Components of Intelligent Agents Representation Language: Graph, Bayes Nets, Linear functions Inference.
MIT CSAIL Vision interfaces Towards efficient matching with random hashing methods… Kristen Grauman Gregory Shakhnarovich Trevor Darrell.
Unsupervised learning
Ivan Laptev IRISA/INRIA, Rennes, France September 07, 2006 Boosted Histograms for Improved Object Detection.
Kernel-based tracking and video patch replacement Igor Guskov
Jointly Aligning and Segmenting Multiple Web Photo Streams for the Inference of Collective Photo Storylines Gunhee Kim Eric P. Xing 1 School of Computer.
Mid-level Visual Element Discovery as Discriminative Mode Seeking Harley Montgomery 11/15/13.
Biased Normalized Cuts 1 Subhransu Maji and Jithndra Malik University of California, Berkeley IEEE Conference on Computer Vision and Pattern Recognition.
CVPR 2008 James Philbin Ondˇrej Chum Michael Isard Josef Sivic
HMM-BASED PATTERN DETECTION. Outline  Markov Process  Hidden Markov Models Elements Basic Problems Evaluation Optimization Training Implementation 2-D.
Unsupervised Learning: Clustering Rong Jin Outline  Unsupervised learning  K means for clustering  Expectation Maximization algorithm for clustering.
1 Unsupervised Modeling and Recognition of Object Categories with Combination of Visual Contents and Geometric Similarity Links Gunhee Kim Christos Faloutsos.
Announcements Project 2 more signup slots questions Picture taking at end of class.
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman ICCV 2003 Presented by: Indriyati Atmosukarto.
1 Unsupervised Modeling of Object Categories Using Link Analysis Techniques Gunhee Kim Christos Faloutsos Martial Hebert Gunhee Kim Christos Faloutsos.
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman University of Oxford ICCV 2003.
1 Segmentation with Scene and Sub-Scene Categories Joseph Djugash Input Image Scene/Sub-Scene Classification Segmentation.
Semi-Supervised Clustering Jieping Ye Department of Computer Science and Engineering Arizona State University
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2006 with a lot of slides stolen from Steve Seitz and.
Spatial Pyramid Pooling in Deep Convolutional
On the Object Proposal Presented by Yao Lu
Radial Basis Function Networks
Generic object detection with deformable part-based models
~5,617,000 population in each state
Image Segmentation Image segmentation is the operation of partitioning an image into a collection of connected sets of pixels. 1. into regions, which usually.
Segmentation and Grouping Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 02/23/10.
Unsupervised Learning of Categories from Sets of Partially Matching Image Features Kristen Grauman and Trevor Darrel CVPR 2006 Presented By Sovan Biswas.
Computer Vision James Hays, Brown
Autonomous Learning of Object Models on Mobile Robots Xiang Li Ph.D. student supervised by Dr. Mohan Sridharan Stochastic Estimation and Autonomous Robotics.
CSE 185 Introduction to Computer Vision Pattern Recognition.
Radial Basis Function Networks
Mean-shift and its application for object tracking
Region Segmentation Readings: Chapter 10: 10.1 Additional Materials Provided K-means Clustering (text) EM Clustering (paper) Graph Partitioning (text)
Adaptive CSMA under the SINR Model: Fast convergence using the Bethe Approximation Krishna Jagannathan IIT Madras (Joint work with) Peruru Subrahmanya.
Random Walk with Restart (RWR) for Image Segmentation
COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
CSE 185 Introduction to Computer Vision Pattern Recognition 2.
CHAPTER 7: Clustering Eick: K-Means and EM (modified Alpaydin transparencies and new transparencies added) Last updated: February 25, 2014.
A Comparative Evaluation of Three Skin Color Detection Approaches Dennis Jensch, Daniel Mohr, Clausthal University Gabriel Zachmann, University of Bremen.
EECS 274 Computer Vision Segmentation by Clustering II.
Deformable Part Models (DPM) Felzenswalb, Girshick, McAllester & Ramanan (2010) Slides drawn from a tutorial By R. Girshick AP 12% 27% 36% 45% 49% 2005.
CS654: Digital Image Analysis Lecture 30: Clustering based Segmentation Slides are adapted from:
Intelligent Database Systems Lab N.Y.U.S.T. I. M. A fast nearest neighbor classifier based on self-organizing incremental neural network (SOINN) Neuron.
Associative Hierarchical CRFs for Object Class Image Segmentation
October Andrew C. Gallagher, Jiebo Luo, Wei Hao Improved Blue Sky Detection Using Polynomial Model Fit Andrew C. Gallagher, Jiebo Luo, Wei Hao Presented.
Image Segmentation Shengnan Wang
Mean Shift ; Theory and Applications Presented by: Reza Hemati دی 89 December گروه بینایی ماشین و پردازش تصویر Machine Vision and Image Processing.
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.
Machine Learning ICS 178 Instructor: Max Welling Supervised Learning.
Object Recognition by Integrating Multiple Image Segmentations Caroline Pantofaru, Cordelia Schmid, Martial Hebert ECCV 2008 E.
Locally Linear Support Vector Machines Ľubor Ladický Philip H.S. Torr.
Feature Selction for SVMs J. Weston et al., NIPS 2000 오장민 (2000/01/04) Second reference : Mark A. Holl, Correlation-based Feature Selection for Machine.
6.S093 Visual Recognition through Machine Learning Competition Image by kirkh.deviantart.com Joseph Lim and Aditya Khosla Acknowledgment: Many slides from.
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman University of Oxford ICCV 2003.
Non-parametric Methods for Clustering Continuous and Categorical Data Steven X. Wang Dept. of Math. and Stat. York University May 13, 2010.
ICCV 2007 National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Half Quadratic Analysis for Mean Shift: with Extension.
Rich feature hierarchies for accurate object detection and semantic segmentation 2014 IEEE Conference on Computer Vision and Pattern Recognition Ross Girshick,
1 Bilinear Classifiers for Visual Recognition Computational Vision Lab. University of California Irvine To be presented in NIPS 2009 Hamed Pirsiavash Deva.
Unsupervised Learning Part 2. Topics How to determine the K in K-means? Hierarchical clustering Soft clustering with Gaussian mixture models Expectation-Maximization.
Semi-Supervised Clustering
Object detection with deformable part-based models
Constrained Clustering -Semi Supervised Clustering-
Video Google: Text Retrieval Approach to Object Matching in Videos
A Consensus-Based Clustering Method
Object detection as supervised classification
Video Google: Text Retrieval Approach to Object Matching in Videos
Presentation transcript:

Unsupervised Detection of Regions of Interest Using Iterative Link Analysis Gunhee Kim 1 Antonio Torralba 2 1: SCS, CMU 2: CSAIL, MIT Neural Information Processing Systems 2009 November 30, 2009

Unsupervised Detection of ROIs A set of images… Rectangular Regions of Interest

Why Is the ROI Detection Useful ? Scene recognition [Quattoni&Torralba, CVPR09] Training for Recognition [Bosch et al, ICCV07] Flickr Notes

Alternating Optimization One of widely used heuristics for iterative optimization Optimization over two sets of variables is not easy But affordable to optimize one while the other is fixed

Goal: Find correspondences between two sets of point clouds [Besl&McKay,1992] Example – Iterative Closest Point Algorithm Trans- formation Estimate transformation parameters Corres- pondences Associate points by NN criteria

Goal: Clustering Example – K-means Cluster Membership Find nearest cluster center Cluster Centers Take mean Initialization Pictures from Bishop’s book

Goal: Find best ROIs in each image of dataset Unsupervised Detection of ROIs Refine ROIs Detection or Localization Find Examplars Modeling or Ranking examplars Where is butterfly? What are examplars?

Our Approach Inspired by alternating optimization Based on link analysis of hypothesis network. Find Examplars = Central and diverse Hubs Refine ROIs = Highly-ranked Hypotheses in each image wrt examplars Easy, Fast and Dynamic –Simple heuristic for linearity of computation wrt dataset size. –Ex. 4.5 hours / 200k images with naïve matlab implementation.

ROI Candidates and Description For each, define –At least one of would be good Description: Spatial pyramids of visual words and HOG Similarity measure: Cosine similarity An image15 segments43 ROI hypotheses Visual wordsEdge Gradient

Algorithm - Input Image set and its ROI hypothesis set

Algorithm - Initialization Best ROI = Image itself !

Algorithm - Initialization Initialization is essential for the success ! Why is it a feasible idea for Web images ? –Most pictures are taken from a canonical view so that an object of interest is located in a center with significant size. –Given a similarity network of a sufficiently large number of images, democratic voting reveals the most dominant visual information as hubs [Kim et al 08] Examples of top-ranked Images

Algorithm – First Hub Seeking Generate a similarity network and find a hub set

Algorithm – First ROI Refinement Bipartite graph between hub sets and All ROIs of an image

Algorithm – Second Hub Seeking Keep iterating…

Hub Seeking with Centrality & Diversity Mean-shift like hub seeking algorithm Mean Shift [Comaniciu and Meer, PAMI 2002] K-NN similarity matrixPageRank vector G (t) K-NN graph Degree distribution ~ PageRank vector

Hub Seeking with Centrality & Diversity Mean-shift like hub seeking algorithm Max P-value ! Fixed radius window = max. reachable probability d (= 0.1) Mean Shift

ROI Refinement Augmented Bipartite Graph (1-α)W o WoTWoT αW i ROI hypothesisHub setvector ROI hypotheses Hub set PageRank Argmax () i

ROI Refinement What does α do? (1-α)W o WoTWoT αW i α = 0α = 0.1 WoWo WoTWoT

Example - ROI Refinement T=0T=1T=2T=3T=4T=5T=6T=7 T=0 T=1 T=2 T=3 T=4 T=5T=6 T=7

Scalability Setting Bottleneck: Quadratic computation to generate a similarity matrix of selected ROIs If dataset size is too large, –Run the algorithm with N number of images ( N = 10,000) –Re-use x % of previous high-ranked images. Dataset N N N N

Experiments Performance Test –PASCAL VOC 2006 Dataset –Weakly-supervised 1 and Unsupervised 2 Scalability Test –Five objects: {butterfly+insect (69,990), classic+car (265,731), motorcycle+bike (106,590), sunflower (165,235), giraffe+zoo (53,620)} –Weakly-supervised 1 1: Input imageset consists of a single object type (only localization is required) 2: Input imageset consists of multiple object types (localization and clustering are required)

Performance Tests Weakly Supervised Localization (PR-Curves) [Russell et al. CVPR 2006] seg discovery/index.html X-axis: Recall Y-axis: Precision

Performance Tests Unsupervised Classification & Localization X-axis: Recall Y-axis: Precision X-axis: FP rate Y-axis: TP rate ROC Curves PR Curves

Scalability Tests Weakly-supervised Localization X-axis: Recall Y-axis: Precision

Perturbation Tests Robustness of ROI detection of each image against random network formation –100 random sets of size of 200 images Entropy: Dataset An image of interest X-axis: ROI hypotheses Y-axis: Frequencies

Localization Examples

Conclusion Alternating optimization based Unsupervised ROI detection Simple and Fast Competitive performance on PASCAL 06 Scalable Test with more than 200K Flickr images Critic: Analysis for convexity, convergence, sensitivity to initialization, quality of solution

Algorithm