SlideShare una empresa de Scribd logo
1 de 17
An Exemplar Model for Learning Object Classes Authors: Ondrej Chum Andrew Zisserman@University of Oxford Presenter: Shao-Chuan Wang
An Exemplar Model for Learning Object Classes Objective: Give training images known to contain instances of an object class, without specifying locations and scales. Detect and localize object Kea Ideas:  Learn region of interest (ROI) around class instance in weakly supervised training data. Based on discriminative features to initialize ROI for the optimization problem
An Exemplar Model for Learning Object Classes Exemplar model: Detection (cost function): X Y X: exemplar set X^w: PHOW descriptor X^e: PHOG descriptor A: aspect ratio of target region d: distance function /mu: mean of exemplars’ aspect ratio /sigma: std of  exemplars’ aspect ratio /alpha, /beta: weighting to be tuned/learned
An Exemplar Model for Learning Object Classes Learning the exemplar model: Learn the regions in all images simultaneously. How to Determine initial ROI? > By discriminative features
Top 10 most discriminative visual words Discriminative features Definition:
Constructing ROI exemplars: Algorithm
Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection. Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection.  Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection. Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
Constructing ROI exemplars: Algorithm Three stages of the optimization process Initialization Optimization Re-initialization via detection
Using the exemplar model Object Detection  Hypothesis Score of a hypothesis n_(w,R): the number of exemplar Images consistent with the hypothesis #w: the number of appearances of the visual word w in the exemplar images Clustering 20 strongest hypotheses are tested on each test image
Using other models Training: Train an SVM, using features within ROI by exemplar models Object detection Scores are ranked by SVM score
Results
Conclusion When constructing exemplars’ ROI, they use discriminability to initialize bounding box In detection, they used relative position of bounding boxes and visual words to try the most probable hypotheses. It may failed to detect when significant class variability in the exemplars, such as people class.

Más contenido relacionado

Similar a An Exemplar Model For Learning Object Classes

Asp netmvc e03
Asp netmvc e03Asp netmvc e03
Asp netmvc e03Yu GUAN
 
Compose Camp session 4.pptx.pdf
Compose Camp session 4.pptx.pdfCompose Camp session 4.pptx.pdf
Compose Camp session 4.pptx.pdfDhruv675089
 
Ml2 train test-splits_validation_linear_regression
Ml2 train test-splits_validation_linear_regressionMl2 train test-splits_validation_linear_regression
Ml2 train test-splits_validation_linear_regressionankit_ppt
 
Easy path to machine learning
Easy path to machine learningEasy path to machine learning
Easy path to machine learningwesley chun
 
Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1Suvadip Shome
 
Avihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slidesAvihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slideswolf
 
Start machine learning in 5 simple steps
Start machine learning in 5 simple stepsStart machine learning in 5 simple steps
Start machine learning in 5 simple stepsRenjith M P
 
Effective testing with pytest
Effective testing with pytestEffective testing with pytest
Effective testing with pytestHector Canto
 
ICMT 2016: Search-Based Model Transformations with MOMoT
ICMT 2016: Search-Based Model Transformations with MOMoTICMT 2016: Search-Based Model Transformations with MOMoT
ICMT 2016: Search-Based Model Transformations with MOMoTMartin Fleck
 
Machine learning and_nlp
Machine learning and_nlpMachine learning and_nlp
Machine learning and_nlpankit_ppt
 
Benchy: Lightweight framework for Performance Benchmarks
Benchy: Lightweight framework for Performance Benchmarks Benchy: Lightweight framework for Performance Benchmarks
Benchy: Lightweight framework for Performance Benchmarks Marcel Caraciolo
 
Tuning 2.0: Advanced Optimization Techniques Webinar
Tuning 2.0: Advanced Optimization Techniques WebinarTuning 2.0: Advanced Optimization Techniques Webinar
Tuning 2.0: Advanced Optimization Techniques WebinarSigOpt
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnBenjamin Bengfort
 
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric StrategyTuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric StrategySigOpt
 
Ensemble Learning Featuring the Netflix Prize Competition and ...
Ensemble Learning Featuring the Netflix Prize Competition and ...Ensemble Learning Featuring the Netflix Prize Competition and ...
Ensemble Learning Featuring the Netflix Prize Competition and ...butest
 
Ch 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-basedCh 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-basedbutest
 
Ch 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-basedCh 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-basedbutest
 
Micro Object Testing
Micro Object TestingMicro Object Testing
Micro Object TestingESUG
 

Similar a An Exemplar Model For Learning Object Classes (20)

Asp netmvc e03
Asp netmvc e03Asp netmvc e03
Asp netmvc e03
 
Compose Camp session 4.pptx.pdf
Compose Camp session 4.pptx.pdfCompose Camp session 4.pptx.pdf
Compose Camp session 4.pptx.pdf
 
Ml2 train test-splits_validation_linear_regression
Ml2 train test-splits_validation_linear_regressionMl2 train test-splits_validation_linear_regression
Ml2 train test-splits_validation_linear_regression
 
Easy path to machine learning
Easy path to machine learningEasy path to machine learning
Easy path to machine learning
 
Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1
 
Avihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slidesAvihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slides
 
Start machine learning in 5 simple steps
Start machine learning in 5 simple stepsStart machine learning in 5 simple steps
Start machine learning in 5 simple steps
 
N046047780
N046047780N046047780
N046047780
 
projectreport
projectreportprojectreport
projectreport
 
Effective testing with pytest
Effective testing with pytestEffective testing with pytest
Effective testing with pytest
 
ICMT 2016: Search-Based Model Transformations with MOMoT
ICMT 2016: Search-Based Model Transformations with MOMoTICMT 2016: Search-Based Model Transformations with MOMoT
ICMT 2016: Search-Based Model Transformations with MOMoT
 
Machine learning and_nlp
Machine learning and_nlpMachine learning and_nlp
Machine learning and_nlp
 
Benchy: Lightweight framework for Performance Benchmarks
Benchy: Lightweight framework for Performance Benchmarks Benchy: Lightweight framework for Performance Benchmarks
Benchy: Lightweight framework for Performance Benchmarks
 
Tuning 2.0: Advanced Optimization Techniques Webinar
Tuning 2.0: Advanced Optimization Techniques WebinarTuning 2.0: Advanced Optimization Techniques Webinar
Tuning 2.0: Advanced Optimization Techniques Webinar
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-Learn
 
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric StrategyTuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
 
Ensemble Learning Featuring the Netflix Prize Competition and ...
Ensemble Learning Featuring the Netflix Prize Competition and ...Ensemble Learning Featuring the Netflix Prize Competition and ...
Ensemble Learning Featuring the Netflix Prize Competition and ...
 
Ch 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-basedCh 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-based
 
Ch 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-basedCh 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-based
 
Micro Object Testing
Micro Object TestingMicro Object Testing
Micro Object Testing
 

Más de Shao-Chuan Wang

Beyond The Euclidean Distance: Creating effective visual codebooks using the ...
Beyond The Euclidean Distance: Creating effective visual codebooks using the ...Beyond The Euclidean Distance: Creating effective visual codebooks using the ...
Beyond The Euclidean Distance: Creating effective visual codebooks using the ...Shao-Chuan Wang
 
A Friendly Guide To Sparse Coding
A Friendly Guide To Sparse CodingA Friendly Guide To Sparse Coding
A Friendly Guide To Sparse CodingShao-Chuan Wang
 
Evaluation Of Color Descriptors For Object And Scene
Evaluation Of Color Descriptors For Object And SceneEvaluation Of Color Descriptors For Object And Scene
Evaluation Of Color Descriptors For Object And SceneShao-Chuan Wang
 
Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and ...
Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and ...Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and ...
Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and ...Shao-Chuan Wang
 
Image Classification And Support Vector Machine
Image Classification And Support Vector MachineImage Classification And Support Vector Machine
Image Classification And Support Vector MachineShao-Chuan Wang
 

Más de Shao-Chuan Wang (9)

Book Cover Recognition
Book Cover RecognitionBook Cover Recognition
Book Cover Recognition
 
Beyond The Euclidean Distance: Creating effective visual codebooks using the ...
Beyond The Euclidean Distance: Creating effective visual codebooks using the ...Beyond The Euclidean Distance: Creating effective visual codebooks using the ...
Beyond The Euclidean Distance: Creating effective visual codebooks using the ...
 
Self Taught Learning
Self Taught LearningSelf Taught Learning
Self Taught Learning
 
A Friendly Guide To Sparse Coding
A Friendly Guide To Sparse CodingA Friendly Guide To Sparse Coding
A Friendly Guide To Sparse Coding
 
Evaluation Of Color Descriptors For Object And Scene
Evaluation Of Color Descriptors For Object And SceneEvaluation Of Color Descriptors For Object And Scene
Evaluation Of Color Descriptors For Object And Scene
 
Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and ...
Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and ...Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and ...
Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and ...
 
Support Vector Machine
Support Vector MachineSupport Vector Machine
Support Vector Machine
 
About Python
About PythonAbout Python
About Python
 
Image Classification And Support Vector Machine
Image Classification And Support Vector MachineImage Classification And Support Vector Machine
Image Classification And Support Vector Machine
 

Último

ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.MaryamAhmad92
 
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptxHMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptxmarlenawright1
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxDenish Jangid
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxVishalSingh1417
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentationcamerronhm
 
Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Association for Project Management
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024Elizabeth Walsh
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...pradhanghanshyam7136
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfPoh-Sun Goh
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...Poonam Aher Patil
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsMebane Rash
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17Celine George
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...ZurliaSoop
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 
Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...
Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...
Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...Pooja Bhuva
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibitjbellavia9
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17Celine George
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - Englishneillewis46
 
Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)Jisc
 

Último (20)

ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptxHMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentation
 
Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdf
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan Fellows
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...
Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...
Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibit
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - English
 
Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)
 

An Exemplar Model For Learning Object Classes

  • 1. An Exemplar Model for Learning Object Classes Authors: Ondrej Chum Andrew Zisserman@University of Oxford Presenter: Shao-Chuan Wang
  • 2. An Exemplar Model for Learning Object Classes Objective: Give training images known to contain instances of an object class, without specifying locations and scales. Detect and localize object Kea Ideas: Learn region of interest (ROI) around class instance in weakly supervised training data. Based on discriminative features to initialize ROI for the optimization problem
  • 3. An Exemplar Model for Learning Object Classes Exemplar model: Detection (cost function): X Y X: exemplar set X^w: PHOW descriptor X^e: PHOG descriptor A: aspect ratio of target region d: distance function /mu: mean of exemplars’ aspect ratio /sigma: std of exemplars’ aspect ratio /alpha, /beta: weighting to be tuned/learned
  • 4. An Exemplar Model for Learning Object Classes Learning the exemplar model: Learn the regions in all images simultaneously. How to Determine initial ROI? > By discriminative features
  • 5. Top 10 most discriminative visual words Discriminative features Definition:
  • 7. Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
  • 8. Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
  • 9. Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
  • 10. Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection. Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
  • 11. Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection. Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
  • 12. Constructing ROI exemplars: Algorithm Initialization Calculate discriminability of visual words Initialize the ROI in each training image by a bounding box of the 64 most discriminative features Optimization of cost function Find the ROI to minimize the cost function with eta = 0 Re-initialization by detection. Refinement Enlarge the ROI in the training images by 10% Calculate discriminability of visual words using only the features inside the ROI Optimization of cost function (goto 2.)
  • 13. Constructing ROI exemplars: Algorithm Three stages of the optimization process Initialization Optimization Re-initialization via detection
  • 14. Using the exemplar model Object Detection Hypothesis Score of a hypothesis n_(w,R): the number of exemplar Images consistent with the hypothesis #w: the number of appearances of the visual word w in the exemplar images Clustering 20 strongest hypotheses are tested on each test image
  • 15. Using other models Training: Train an SVM, using features within ROI by exemplar models Object detection Scores are ranked by SVM score
  • 17. Conclusion When constructing exemplars’ ROI, they use discriminability to initialize bounding box In detection, they used relative position of bounding boxes and visual words to try the most probable hypotheses. It may failed to detect when significant class variability in the exemplars, such as people class.