Semi-supervised Mesh Segmentation and Labeling

Slides:



Advertisements
Similar presentations
Complex Networks for Representation and Characterization of Images For CS790g Project Bingdong Li 9/23/2009.
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.
Co Training Presented by: Shankar B S DMML Lab
Foreground Focus: Finding Meaningful Features in Unlabeled Images Yong Jae Lee and Kristen Grauman University of Texas at Austin.
Interactively Co-segmentating Topically Related Images with Intelligent Scribble Guidance Dhruv Batra, Carnegie Mellon University Adarsh Kowdle, Cornell.
Semantic Texton Forests for Image Categorization and Segmentation We would like to thank Amnon Drory for this deck הבהרה : החומר המחייב הוא החומר הנלמד.
Learning to estimate human pose with data driven belief propagation Gang Hua, Ming-Hsuan Yang, Ying Wu CVPR 05.
Intelligent Systems Lab. Recognizing Human actions from Still Images with Latent Poses Authors: Weilong Yang, Yang Wang, and Greg Mori Simon Fraser University,
Discriminative Segment Annotation in Weakly Labeled Video Kevin Tang, Rahul Sukthankar Appeared in CVPR 2013 (Oral)
A Probabilistic Framework for Semi-Supervised Clustering
Presented by Arshad Jamal, Rajesh Dhania, Vinkal Vishnoi Active hashing and its application to image and text retrieval Yi Zhen, Dit-Yan Yeung, Published.
Learning using Graph Mincuts Shuchi Chawla Carnegie Mellon University 1/11/2003.
Self Taught Learning : Transfer learning from unlabeled data Presented by: Shankar B S DMML Lab Rajat Raina et al, CS, Stanford ICML 2007.
Robust Higher Order Potentials For Enforcing Label Consistency
Unsupervised Learning: Clustering Rong Jin Outline  Unsupervised learning  K means for clustering  Expectation Maximization algorithm for clustering.
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.
Abstract We present a model of curvilinear grouping using piecewise linear representations of contours and a conditional random field to capture continuity.
Learning 3D mesh segmentation and labeling Evangelos Kalogerakis, Aaron Hertzmann, Karan Singh University of Toronto Head Tors o Upper arm Lower arm Hand.
Three kinds of learning
Dept. of Computer Science & Engineering, CUHK Pseudo Relevance Feedback with Biased Support Vector Machine in Multimedia Retrieval Steven C.H. Hoi 14-Oct,
Hierarchical Subquery Evaluation for Active Learning on a Graph Oisin Mac Aodha, Neill Campbell, Jan Kautz, Gabriel Brostow CVPR 2014 University College.
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.
Prior Knowledge for Part Correspondence Oliver van Kaick 1, Andrea Tagliasacchi 1, Oana Sidi 2, Hao Zhang 1, Daniel Cohen-Or 2, Lior Wolf 2, Ghassan Hamarneh.
Jinhui Tang †, Shuicheng Yan †, Richang Hong †, Guo-Jun Qi ‡, Tat-Seng Chua † † National University of Singapore ‡ University of Illinois at Urbana-Champaign.
Final review LING572 Fei Xia Week 10: 03/11/
Social Network Analysis via Factor Graph Model
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
Active Learning for Class Imbalance Problem
Learning with Positive and Unlabeled Examples using Weighted Logistic Regression Wee Sun Lee National University of Singapore Bing Liu University of Illinois,
Data mining and machine learning A brief introduction.
Interactive surface reconstruction on triangle meshes with subdivision surfaces Matthias Bein Fraunhofer-Institut für Graphische Datenverarbeitung IGD.
LOGO Ensemble Learning Lecturer: Dr. Bo Yuan
A Weakly-Supervised Approach to Argumentative Zoning of Scientific Documents Yufan Guo Anna Korhonen Thierry Poibeau 1 Review By: Pranjal Singh Paper.
Xiangnan Kong,Philip S. Yu Department of Computer Science University of Illinois at Chicago KDD 2010.
Supervised Learning of Edges and Object Boundaries Piotr Dollár Zhuowen Tu Serge Belongie.
Mining Social Network for Personalized Prioritization Language Techonology Institute School of Computer Science Carnegie Mellon University Shinjae.
Shape Analysis and Deformation Igarashi Lab M2 Akira Ohgawara.
A Novel Local Patch Framework for Fixing Supervised Learning Models Yilei Wang 1, Bingzheng Wei 2, Jun Yan 2, Yang Hu 2, Zhi-Hong Deng 1, Zheng Chen 2.
Computer Vision Michael Isard and Dimitris Metaxas.
Prototype-Driven Learning for Sequence Models Aria Haghighi and Dan Klein University of California Berkeley Slides prepared by Andrew Carlson for the Semi-
Paired Sampling in Density-Sensitive Active Learning Pinar Donmez joint work with Jaime G. Carbonell Language Technologies Institute School of Computer.
Tell Me What You See and I will Show You Where It Is Jia Xu 1 Alexander G. Schwing 2 Raquel Urtasun 2,3 1 University of Wisconsin-Madison 2 University.
Training Conditional Random Fields using Virtual Evidence Boosting Lin Liao, Tanzeem Choudhury †, Dieter Fox, and Henry Kautz University of Washington.
COP5992 – DATA MINING TERM PROJECT RANDOM SUBSPACE METHOD + CO-TRAINING by SELIM KALAYCI.
Sponsored by Deformation-Driven Topology-Varying 3D Shape Correspondence Ibraheem Alhashim Kai Xu Yixin Zhuang Junjie Cao Patricio Simari Hao Zhang Presenter:
Multi Scale CRF Based RGB-D Image Segmentation Using Inter Frames Potentials Taha Hamedani Robot Perception Lab Ferdowsi University of Mashhad The 2 nd.
Contextual models for object detection using boosted random fields by Antonio Torralba, Kevin P. Murphy and William T. Freeman.
Machine Learning in Practice Lecture 24 Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Object Recognition by Integrating Multiple Image Segmentations Caroline Pantofaru, Cordelia Schmid, Martial Hebert ECCV 2008 E.
Efficient Belief Propagation for Image Restoration Qi Zhao Mar.22,2006.
CAD Mesh Model Segmentation by Clustering
IEEE 2015 Conference on Computer Vision and Pattern Recognition Active Learning for Structured Probabilistic Models with Histogram Approximation Qing SunAnkit.
Max-Confidence Boosting With Uncertainty for Visual tracking WEN GUO, LIANGLIANG CAO, TONY X. HAN, SHUICHENG YAN AND CHANGSHENG XU IEEE TRANSACTIONS ON.
Presenter: Jae Sung Park
Gaussian Conditional Random Field Network for Semantic Segmentation
Machine learning & object recognition Cordelia Schmid Jakob Verbeek.
Introduction to Machine Learning Nir Ailon Lecture 12: EM, Clustering and More.
Scalable Person Re-identification on Supervised Smoothed Manifold
Prior Knowledge for Part Correspondence
Summary of “Efficient Deep Learning for Stereo Matching”
Semi-supervised Machine Learning Gergana Lazarova
Anatomical Model Labeled
Restricted Boltzmann Machines for Classification
Nonparametric Semantic Segmentation
Binghui Wang, Le Zhang, Neil Zhenqiang Gong
Learning 3D mesh segmentation and labeling
Semi-Supervised Learning
“Traditional” image segmentation
Anatomical Model Unlabeled
Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision.
Presentation transcript:

Semi-supervised Mesh Segmentation and Labeling asd Semi-supervised Mesh Segmentation and Labeling Jiajun Lv, Xinlei Chen, Jin Huang, Hujun Bao State Key Lab of CAD&CG, Zhejiang University

Motivation Recognition of Mesh Semantic Meanings Head Torso Upper arm asd Motivation Recognition of Mesh Semantic Meanings Head Torso Upper arm Lower arm Hand Upper leg Lower leg Foot

asd Motivation 3D Modeling

Related Work Geometric Structure Based Approaches asd Related Work Geometric Structure Based Approaches Drawbacks: No Suitable Geometric Feature Data-driven Supervised Approaches Drawbacks: Large Size of Training Dataset Unsupervised Co-Segmentation Approaches Drawbacks: Inferior to Supervised Method

Related Work Head Neck Torso Leg Tail Ear asd Related Work Head Neck Torso Leg Tail Ear Learning 3d mesh segmentation and labeling, KALOGERAKIS E., 2010 Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering, SIDI O., 2011 Learning boundary edges for 3D-mesh segmentation, BENHABILES H., 2011 Joint shape segmentation with linear programming, HUANG Q., 2011

Semi-Supervised Learning asd Semi-Supervised Learning

Semi-Supervised Learning asd Semi-Supervised Learning

asd Method

Key Technical Points Per-mesh Conditional Random Fields Model asd Key Technical Points Per-mesh Conditional Random Fields Model Incorporation of unlabeled mesh information with an entropy term Learning Parameters with Virtual Evidence Boosting

Definition Unary Features Labeled Meshes Semi-supervised asd Definition Unary Features Labeled Meshes Semi-supervised Mesh Segmentation Pairwise Features Unlabeled Meshes

Per-mesh Conditional Random Fields Model asd Per-mesh Conditional Random Fields Model

Incorporation of unlabeled mesh information with an entropy term asd Incorporation of unlabeled mesh information with an entropy term Information Gain: Negative Conditional Entropy of the CRF on Unlabeled Meshes Greater Certainty

Learning Parameters with Virtual Evidence Boosting asd Learning Parameters with Virtual Evidence Boosting

asd Learning Parameters with Virtual Evidence Boosting----Belief Propagation Information about distribution of sending node Information about which values recipient node should prefer

Learning Parameters with Virtual Evidence Boosting----LogitBoost asd Learning Parameters with Virtual Evidence Boosting----LogitBoost 1. Unary Energy Term 2. Pairwise Energy Term

Results and Discussion asd Results and Discussion

asd Results The segmentation and labeling results of our semi-supervised mesh segmentation algorithm on the whole Princeton Segmentation Benchmark

asd Results Experimental results of the semi-supervised mesh segmentation method. For each kind of dataset, the left column three are the labeled training dataset, and the right column three are the segmented meshes.

asd Results Comparison of Supervised and Semi-supervised Approaches

asd Results Semi-supervised Approach with Different Labeled Training Meshes

asd Robustness Noise of the labeled set is inevitable, such as human mislabeling Entropy term acts as a regularizer, avoiding over- fitting to training data

asd Robustness Comparison of Supervised and Semi-supervised Approaches on Inconsistent Labeled Data

Complexity of The Method asd Complexity of The Method Training Complexity Each Belief Propagation: Each Boosting Iteration: Labeling Complexity All Belief Propagation: All Boosting Iteration: Time Consumption Training: 7-12hours Labeling: a few minutes

Limitation Manually tuning parameters Jagged and Disconnect Patches asd Limitation Manually tuning parameters Jagged and Disconnect Patches Mesh with weak features

Future Work Hierarchical Models asd Future Work Hierarchical Models Partially Labeled Semi-supervised Mesh Segmentation

Thank You For Your Attention ! asd Thank You For Your Attention !