CVR05 University of California Berkeley 1 Cue Integration in Figure/Ground Labeling Xiaofeng Ren, Charless Fowlkes, Jitendra Malik.

Slides:



Advertisements
Similar presentations
Shape Matching and Object Recognition using Low Distortion Correspondence Alexander C. Berg, Tamara L. Berg, Jitendra Malik U.C. Berkeley.
Advertisements

POSE–CUT Simultaneous Segmentation and 3D Pose Estimation of Humans using Dynamic Graph Cuts Mathieu Bray Pushmeet Kohli Philip H.S. Torr Department of.
Pose Estimation and Segmentation of People in 3D Movies Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev Inria, Ecole Normale Superieure ICCV.
November 12, 2013Computer Vision Lecture 12: Texture 1Signature Another popular method of representing shape is called the signature. In order to compute.
Agenda Introduction Bag-of-words models Visual words with spatial location Part-based models Discriminative methods Segmentation and recognition Recognition-based.
Learning to Combine Bottom-Up and Top-Down Segmentation Anat Levin and Yair Weiss School of CS&Eng, The Hebrew University of Jerusalem, Israel.
Shape Sharing for Object Segmentation
Recovering Human Body Configurations: Combining Segmentation and Recognition Greg Mori, Xiaofeng Ren, and Jitentendra Malik (UC Berkeley) Alexei A. Efros.
Exact Inference in Bayes Nets
Carolina Galleguillos, Brian McFee, Serge Belongie, Gert Lanckriet Computer Science and Engineering Department Electrical and Computer Engineering Department.
Parsing Clothing in Fashion Photographs
Qualifying Exam: Contour Grouping Vida Movahedi Supervisor: James Elder Supervisory Committee: Minas Spetsakis, Jeff Edmonds York University Summer 2009.
ADS lab NCKU1 Michael Maire, Pablo Arbelaez, Charless Fowlkes, and Jitendra Malik university of California, Berkeley – Berkeley university of California,
1 Contours and Junctions in Natural Images Jitendra Malik University of California at Berkeley (with Jianbo Shi, Thomas Leung, Serge Belongie, Charless.
Ghunhui Gu, Joseph J. Lim, Pablo Arbeláez, Jitendra Malik University of California at Berkeley Berkeley, CA
A Graphical Model For Simultaneous Partitioning And Labeling Philip Cowans & Martin Szummer AISTATS, Jan 2005 Cambridge.
Computer Vision Group University of California Berkeley Estimating Human Body Configurations using Shape Context Matching Greg Mori and Jitendra Malik.
Learning to Detect A Salient Object Reporter: 鄭綱 (3/2)
Recognition using Regions CVPR Outline Introduction Overview of the Approach Experimental Results Conclusion.
Computer Vision Group University of California Berkeley 1 Learning Scale-Invariant Contour Completion Xiaofeng Ren, Charless Fowlkes and Jitendra Malik.
Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues David R. Martin Charless C. Fowlkes Jitendra Malik.
Abstract We present a model of curvilinear grouping using piecewise linear representations of contours and a conditional random field to capture continuity.
Measuring the Ecological Statistics of Figure-Ground Charless Fowlkes, David Martin, Jitendra Malik.
1 Learning to Detect Natural Image Boundaries David Martin, Charless Fowlkes, Jitendra Malik Computer Science Division University of California at Berkeley.
CVR05 University of California Berkeley 1 Familiar Configuration Enables Figure/Ground Assignment in Natural Scenes Xiaofeng Ren, Charless Fowlkes, Jitendra.
Computer Vision Group University of California Berkeley Visual Grouping and Object Recognition Jitendra Malik * U.C. Berkeley * with S. Belongie, C. Fowlkes,
Berkeley Vision GroupNIPS Vancouver Learning to Detect Natural Image Boundaries Using Local Brightness,
Measuring the Ecological Statistics of Figure-Ground Charless Fowlkes, David Martin, Jitendra Malik.
A Database of Human Segmented Natural Images and Two Applications David Martin, Charless Fowlkes, Doron Tal, Jitendra Malik UC Berkeley
1 The Ecological Statistics of Grouping by Similarity Charless Fowlkes, David Martin, Jitendra Malik Computer Science Division University of California.
Computer Vision Group University of California Berkeley 1 Scale-Invariant Random Fields for Mid-level Vision Xiaofeng Ren, Charless Fowlkes and Jitendra.
Visual Grouping and Recognition David Martin UC Berkeley David Martin UC Berkeley.
Probabilistic Models for Parsing Images Xiaofeng Ren University of California, Berkeley.
Understanding Belief Propagation and its Applications Dan Yuan June 2004.
MSRI University of California Berkeley 1 Recovering Human Body Configurations using Pairwise Constraints between Parts Xiaofeng Ren, Alex Berg, Jitendra.
Belief Propagation Kai Ju Liu March 9, Statistical Problems Medicine Finance Internet Computer vision.
On Measuring * the Ecological Validity of Local Figure-Ground Cues Charless Fowlkes, David Martin, Jitendra Malik Computer Science Division University.
1 Occlusions – the world is flat without them! : Learning-Based Methods in Vision A. Efros, CMU, Spring 2009.
1 How do ideas from perceptual organization relate to natural scenes?
1 Ecological Statistics and Perceptual Organization Charless Fowlkes work with David Martin and Jitendra Malik at University of California at Berkeley.
Computer Vision Group University of California Berkeley 1 Cue Integration in Figure/Ground Labeling Xiaofeng Ren, Charless Fowlkes and Jitendra Malik.
Cue Integration in Figure/Ground Labeling Xiaofeng Ren, Charless Fowlkes and Jitendra Malik, U.C. Berkeley We present a model of edge and region grouping.
A Trainable Graph Combination Scheme for Belief Propagation Kai Ju Liu New York University.
7-1 Introduction The field of statistical inference consists of those methods used to make decisions or to draw conclusions about a population. These.
Heather Dunlop : Advanced Perception January 25, 2006
Active Learning for Networked Data Based on Non-progressive Diffusion Model Zhilin Yang, Jie Tang, Bin Xu, Chunxiao Xing Dept. of Computer Science and.
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
Linked Edges as Stable Region Boundaries* Michael Donoser, Hayko Riemenschneider and Horst Bischof This work introduces an unsupervised method to detect.
Boltzmann Machines and their Extensions S. M. Ali Eslami Nicolas Heess John Winn March 2013 Heriott-Watt University.
Techniques for Estimating Layers from Polar Radar Imagery Jerome E. Mitchell, Geoffrey C. Fox, and David J. Crandall :: CReSIS NSF Site Visit :: School.
1 Contours and Junctions in Natural Images Jitendra Malik University of California at Berkeley (with Jianbo Shi, Thomas Leung, Serge Belongie, Charless.
Multiscale Symmetric Part Detection and Grouping Alex Levinshtein, Sven Dickinson, University of Toronto and Cristian Sminchisescu, University of Bonn.
7-1 Introduction The field of statistical inference consists of those methods used to make decisions or to draw conclusions about a population. These.
Markov Random Fields Probabilistic Models for Images
Automatic Image Annotation by Using Concept-Sensitive Salient Objects for Image Content Representation Jianping Fan, Yuli Gao, Hangzai Luo, Guangyou Xu.
28 February, 2003University of Glasgow1 Cluster Variation Method and Probabilistic Image Processing -- Loopy Belief Propagation -- Kazuyuki Tanaka Graduate.
John Lafferty Andrew McCallum Fernando Pereira
Markov Random Fields & Conditional Random Fields
1 Chapter 8: Model Inference and Averaging Presented by Hui Fang.
Discriminative Training and Machine Learning Approaches Machine Learning Lab, Dept. of CSIE, NCKU Chih-Pin Liao.
Edge Preserving Spatially Varying Mixtures for Image Segmentation Giorgos Sfikas, Christophoros Nikou, Nikolaos Galatsanos (CVPR 2008) Presented by Lihan.
Learning Coordination Classifiers
Sublinear Computational Time Modeling in Statistical Machine Learning Theory for Markov Random Fields Kazuyuki Tanaka GSIS, Tohoku University, Sendai,
7-1 Introduction The field of statistical inference consists of those methods used to make decisions or to draw conclusions about a population. These.
Nonparametric Semantic Segmentation
Context-Aware Modeling and Recognition of Activities in Video
Contours and Junctions in Natural Images
Learning to Combine Bottom-Up and Top-Down Segmentation
Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation Binghui Wang, Jinyuan Jia, and Neil.
Learning complex visual concepts
Presentation transcript:

CVR05 University of California Berkeley 1 Cue Integration in Figure/Ground Labeling Xiaofeng Ren, Charless Fowlkes, Jitendra Malik

CVR05 University of California Berkeley 2 Introduction CRF Conditional Random Fields on triangulated images, trained to integrate low/mid/high-level grouping cues Approach:

CVR05 University of California Berkeley 3 Joint Contour/Region Inference Xe Yt Contour variables{Xe} Region variables{Yt} Object variables{Z} Z Integrating {Xe},{Yt} and{Z}: low/mid/high-level cues

CVR05 University of California Berkeley 4 Grouping Cues Low-level Cues –Edge energy along edge e –Brightness/texture similarity between two regions s and t Mid-level Cues –Edge collinearity and junction frequency at vertex V –Consistency between edge e and two adjoining regions s and t High-level Cues –Texture similarity of region t to exemplars –Compatibility of region shape with pose –Compatibility of local edge shape with pose Low-level Cues –Edge energy along edge e –Brightness/texture similarity between two regions s and t Mid-level Cues –Edge collinearity and junction frequency at vertex V –Consistency between edge e and two adjoining regions s and t High-level Cues –Texture similarity of region t to exemplars –Compatibility of region shape with pose –Compatibility of local edge shape with pose L 1 (X e |I) L 2 (Y s,Y t |I) M 1 (X V |I) M 2 (X e,Y s,Y t ) H 1 (Y t |I) H 2 (Y t,Z|I) H 3 (X e,Z|I)

CVR05 University of California Berkeley 5 Conditional Random Fields for Cue Integration Estimate the marginal posteriors of X, Y and Z

CVR05 University of California Berkeley 6 H 3 (X e,Z|I): local shape and pose shapeme i (horizontal line) distribution ON(x,y,i) shapeme j (vertical pairs) distribution ON(x,y,j) Let S(x,y) be the shapeme at image location (x,y); (x o,y o ) be the object location in Z. Compute average log likelihood S ON (e,Z) as: Then we have: S OFF (e,Z) is defined similarly.

CVR05 University of California Berkeley 7 Training/Testing Trained on half (172) of the grayscale horse images from the [Borenstein & Ullman 02] Horse Dataset. Use human-marked segmentations to construct groundtruth labels on both CDT edges and triangles. Uses loopy belief propagation for approximate inference; takes < 1 second to converge for a typical image. Parameter estimation with gradient descent for maximum likelihood; converges in 1000 iterations. Tested on the other half of the horse images in grayscale. Quantitative evaluation against groundtruth: precision- recall curves for both contours and regions. Trained on half (172) of the grayscale horse images from the [Borenstein & Ullman 02] Horse Dataset. Use human-marked segmentations to construct groundtruth labels on both CDT edges and triangles. Uses loopy belief propagation for approximate inference; takes < 1 second to converge for a typical image. Parameter estimation with gradient descent for maximum likelihood; converges in 1000 iterations. Tested on the other half of the horse images in grayscale. Quantitative evaluation against groundtruth: precision- recall curves for both contours and regions.

CVR05 University of California Berkeley 8

CVR05 University of California Berkeley 9

CVR05 University of California Berkeley 10 Results InputInput PbOutput ContourOutput Figure

CVR05 University of California Berkeley 11 InputInput PbOutput ContourOutput Figure

CVR05 University of California Berkeley 12 InputInput PbOutput ContourOutput Figure

CVR05 University of California Berkeley 13 Conclusion

CVR05 University of California Berkeley 14 Thank You

CVR05 University of California Berkeley 15