Jifeng Dai 2011/09/27.  Introduction  Structural SVM  Kernel Design  Segmentation and parameter learning  Object Feature Descriptors  Experimental.

Slides:



Advertisements
Similar presentations
PHONE MODELING AND COMBINING DISCRIMINATIVE TRAINING FOR MANDARIN-ENGLISH BILINGUAL SPEECH RECOGNITION Yanmin Qian, Jia Liu ICASSP2010 Pei-Ning Chen CSIE.
Advertisements

(SubLoc) Support vector machine approach for protein subcelluar localization prediction (SubLoc) Kim Hye Jin Intelligent Multimedia Lab
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.
Face Alignment by Explicit Shape Regression
Location Recognition Given: A query image A database of images with known locations Two types of approaches: Direct matching: directly match image features.
ECG Signal processing (2)
Recognizing Human Actions by Attributes CVPR2011 Jingen Liu, Benjamin Kuipers, Silvio Savarese Dept. of Electrical Engineering and Computer Science University.
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
On-line learning and Boosting
1 Challenge the future HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences Omar Oreifej Zicheng Liu CVPR 2013.
Carolina Galleguillos, Brian McFee, Serge Belongie, Gert Lanckriet Computer Science and Engineering Department Electrical and Computer Engineering Department.
Structured SVM Chen-Tse Tsai and Siddharth Gupta.
Pattern Recognition and Machine Learning
Classification using intersection kernel SVMs is efficient Joint work with Subhransu Maji and Alex Berg Jitendra Malik UC Berkeley.
Machine learning continued Image source:
- Recovering Human Body Configurations: Combining Segmentation and Recognition (CVPR’04) Greg Mori, Xiaofeng Ren, Alexei A. Efros and Jitendra Malik -
LPP-HOG: A New Local Image Descriptor for Fast Human Detection Andy Qing Jun Wang and Ru Bo Zhang IEEE International Symposium.
Ziming Zhang*, Ze-Nian Li, Mark Drew School of Computing Science Simon Fraser University Vancouver, Canada {zza27, li, AdaMKL: A Novel.
Contour Based Approaches for Visual Object Recognition Jamie Shotton University of Cambridge Joint work with Roberto Cipolla, Andrew Blake.
Detecting Pedestrians by Learning Shapelet Features
Fast intersection kernel SVMs for Realtime Object Detection
Discriminative and generative methods for bags of features
Content Based Image Clustering and Image Retrieval Using Multiple Instance Learning Using Multiple Instance Learning Xin Chen Advisor: Chengcui Zhang Department.
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
1 Integrating User Feedback Log into Relevance Feedback by Coupled SVM for Content-Based Image Retrieval 9-April, 2005 Steven C. H. Hoi *, Michael R. Lyu.
Image Categorization by Learning and Reasoning with Regions Yixin Chen, University of New Orleans James Z. Wang, The Pennsylvania State University Published.
Machine Learning in Simulation-Based Analysis 1 Li-C. Wang, Malgorzata Marek-Sadowska University of California, Santa Barbara.
An Introduction to Support Vector Machines Martin Law.
Graph-based consensus clustering for class discovery from gene expression data Zhiwen Yum, Hau-San Wong and Hongqiang Wang Bioinformatics, 2007.
Learning Visual Bits with Direct Feature Selection Joel Jurik 1 and Rahul Sukthankar 2,3 1 University of Central Florida 2 Intel Research Pittsburgh 3.
Shape-Based Human Detection and Segmentation via Hierarchical Part- Template Matching Zhe Lin, Member, IEEE Larry S. Davis, Fellow, IEEE IEEE TRANSACTIONS.
Object Bank Presenter : Liu Changyu Advisor : Prof. Alex Hauptmann Interest : Multimedia Analysis April 4 th, 2013.
CS 8751 ML & KDDSupport Vector Machines1 Support Vector Machines (SVMs) Learning mechanism based on linear programming Chooses a separating plane based.
Professor: S. J. Wang Student : Y. S. Wang
Multiscale Symmetric Part Detection and Grouping Alex Levinshtein, Sven Dickinson, University of Toronto and Cristian Sminchisescu, University of Bonn.
Machine Learning Seminar: Support Vector Regression Presented by: Heng Ji 10/08/03.
Detecting Curved Symmetric Parts using a Deformable Disc Model Tom Sie Ho Lee, University of Toronto Sanja Fidler, TTI Chicago Sven Dickinson, University.
Efficient Region Search for Object Detection Sudheendra Vijayanarasimhan and Kristen Grauman Department of Computer Science, University of Texas at Austin.
A hybrid SOFM-SVR with a filter-based feature selection for stock market forecasting Huang, C. L. & Tsai, C. Y. Expert Systems with Applications 2008.
Classifiers Given a feature representation for images, how do we learn a model for distinguishing features from different classes? Zebra Non-zebra Decision.
An Introduction to Support Vector Machines (M. Law)
INTRODUCTION Heesoo Myeong and Kyoung Mu Lee Department of ECE, ASRI, Seoul National University, Seoul, Korea Tensor-based High-order.
Exploiting Context Analysis for Combining Multiple Entity Resolution Systems -Ramu Bandaru Zhaoqi Chen Dmitri V.kalashnikov Sharad Mehrotra.
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.
Chao-Yeh Chen and Kristen Grauman University of Texas at Austin Efficient Activity Detection with Max- Subgraph Search.
Easiest-to-Reach Neighbor Search Fatimah Aldubaisi.
Gang WangDerek HoiemDavid Forsyth. INTRODUCTION APROACH (implement detail) EXPERIMENTS CONCLUSION.
Learning Spectral Clustering, With Application to Speech Separation F. R. Bach and M. I. Jordan, JMLR 2006.
1 CSCI 3202: Introduction to AI Decision Trees Greg Grudic (Notes borrowed from Thomas G. Dietterich and Tom Mitchell) Intro AIDecision Trees.
1 Classification and Feature Selection Algorithms for Multi-class CGH data Jun Liu, Sanjay Ranka, Tamer Kahveci
Recognition Using Visual Phrases
Final Exam Review CS479/679 Pattern Recognition Dr. George Bebis 1.
Object Recognition as Ranking Holistic Figure-Ground Hypotheses Fuxin Li and Joao Carreira and Cristian Sminchisescu 1.
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.
A distributed PSO – SVM hybrid system with feature selection and parameter optimization Cheng-Lung Huang & Jian-Fan Dun Soft Computing 2008.
Parsing Natural Scenes and Natural Language with Recursive Neural Networks INTERNATIONAL CONFERENCE ON MACHINE LEARNING (ICML 2011) RICHARD SOCHER CLIFF.
Support Vector Machine Slides from Andrew Moore and Mingyue Tan.
PREDICT 422: Practical Machine Learning
Compact Bilinear Pooling
Object detection with deformable part-based models
Paper Presentation: Shape and Matching
Hyper-parameter tuning for graph kernels via Multiple Kernel Learning
Object detection as supervised classification
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Cheng-Ming Huang, Wen-Hung Liao Department of Computer Science
Janardhan Rao (Jana) Doppa, Alan Fern, and Prasad Tadepalli
“The Truth About Cats And Dogs”
RCNN, Fast-RCNN, Faster-RCNN
Learning Incoherent Sparse and Low-Rank Patterns from Multiple Tasks
Boris Babenko, Steve Branson, Serge Belongie
Presentation transcript:

Jifeng Dai 2011/09/27

 Introduction  Structural SVM  Kernel Design  Segmentation and parameter learning  Object Feature Descriptors  Experimental results  Conclusions and Future Work

CVPR 2011 Oral

 Things to do:

 Contributions: 1) Propose a kernelized structural support vector machine approach to learn discriminatively the mapping from image to a segmentation mask. 2) Combine high level object similarity information with multiple low level segmentation cues into a novel kernel. 3) Traditional segmentation regularizations are preserved in the framework and explicitly enforced during the learning process. This way smoothness of the solution does not need to be “re-learned” from training examples.

 Complex output The dog chased the cat x S VPNP DetNV NP DetN y2y2 S VP DetNV NP VN y1y1 S VP DetNV NP DetN ykyk …

 Training Examples:  Hypothesis Space: The dog chased the cat x S VPNP DetNV NP DetN y1y1 S VP DetNV NP VN y2y2 S VP DetNV NP DetN y 58 S VPNP DetNV NP DetN y 12 S VPNP DetNV NP DetN y 34 S VPNP DetNV NP DetN y4y4 Training: Find that solve Problems How to predict efficiently? How to learn efficiently? Manageable number of parameters?

 The idea behind Structured SVM is to discriminatively learn a scoring function over input/output pairs (i.e. over image/mask pairs).

 Loss function:  Two important choices: 1) Restrict the search to Ys, subset of Y composed by smooth segmentation masks.

 Two important choices: 1) Restrict the search to Ys, subset of Y composed by smooth segmentation masks. 2) using kernel functions so that we could work in the dual formulation.

HOG… Object Similarity Kernel Mask Similarity Kernel

1) Shape Kernel 2) Local Color Model Kernel 3) Global Color Model Kernel

 Graph cuts Mask smooth term In which So (6) and (7) take the form: Graph cuts!!!

 Parameters are optimized on a validation set

 HOG grid or detector response feature

 Datasets: 1) the Dresses dataset (600 images) 2) the Weizmann horses dataset (328 images) 3) the Oxford 17 category flower dataset (849 images)

 How to measure performance?

 Comparison with previous works:

Oxford Flower Dataset Previous work:

 Examples:

Contributions: 1) Propose a kernelized structural support vector machine approach to learn discriminatively the mapping from image to a segmentation mask. 2) Combine high level object similarity information with multiple low level segmentation cues into a novel kernel. 3) Traditional segmentation regularizations are preserved in the framework and explicitly enforced during the learning process. This way smoothness of the solution does not need to be “re-learned” from training examples.

Future Work: 1)Model the boundary curves (driven by low-level cues). 2) Instead of relying on a single global object similarity kernel, dividing the kernel into a parts-based representation. 3) Establish a theoretical connection between the complexity of the top-down models the algorithm can learn and the number of segmentations needed in the training set.