SlideShare une entreprise Scribd logo
1  sur  34
+
FAME:
Face Association
through Model
Evolution
Pinar Duygulu (CMU, Hacettepe University)
Eren Golge (Bilkent University)
+
Yale dataset:
10 subjects, 9 poses, 64 illuminations
Labelled Faces in the wild
13323 Faces of 5749 celebrities
PubFig dataset
60,000 images of 200 people
Social Face Classification
4.4 million labeled faces from
4,030 people
+
Labeling for how many?
+
Search web for faces of a query name
+
Use this set to learn models
+
Variations and sub-categories
+
Irrelevant people
+
Find category related images in
the set of weakly labeled images
+Our previous work: Densest component
Most similar set of faces as a subgraph
Assumption:
The most similar
subset of faces
among the faces
associated with a
name will be the
correct faces
Drawback:
Finds a single
subset
Ozkan, D., Duygulu, P., ”Interesting Faces: A Graph Based Approach for Finding People in News”, Pattern
Recognition, 2010
Ozkan, D., Duygulu, P., ”A Graph Based Approach for Naming Faces in News Photos”, CVPR, 2006
Ozkan, D., Duygulu, P., ”Finding People Frequently Appearing in News”, CIVR, 2006
+
Our previous work: Concept Maps
Grouping and outlier removal
Golge, E., Duygulu, P., “Concept Maps: Mining Noisy Web Data for Concept Learning ”, accepted
+ Our previous work: Concept Maps
Grouping and outlier removal
Assumption:
Faces of a single
person can have sub-
categories
Outliers are different
than the queried
person
Drawback:
Eliminates strange
looks not in groups
as well
+
FAME
Face Association through Model Evolution
Capture discriminative and representative category
images through iterative data cleansing
Separate category instances versus random images.
Agnostic data refining method against Irrelevancy.
Evade Sub-Grouping using very high dimensional
representations.
+ Overview of FAME
First discern category candidates (CC) from random set (RS).
Define category references(CR) inside CC .
Second discern CR from CC.
Define spurious instances (SI) against CR and eliminate.
Re-Iterate
+
Step 1
Discerning category from random set
Learn a linear model M1 betweencategory
candidates CC and random set RS.
Take the most confidently classified instances
as the category references CR.
+
Step 2
Discerning category references from others
Another model M2 between category references
CR and other category candidates.
+
Step 3
Define spurious instances SI against category references CR.
Eliminate SI.
+ FAME
+
Eliminations by iteration
+
Eliminations by iteration
+
High Dimensional Representation
High dimensions help a category linearly separable
from others despite of category modularity.
+
Feature learning
Coates, Adam, Andrew Y. Ng, and Honglak Lee. "An analysis of single-layer networks in unsupervised feature
learning." International Conference on Artificial Intelligence and Statistics. 2011.
+
Raw pixel LBP encoded outliers
+
Implementation details
FAME
Data refining : L1 Logistic Regression with Gauss-Seidel algorithm [1]
Final Classifier: L1 Linear SVM with Grafting[2].
At each iteration 5 images are eliminated.
Feature Learning
Augment train data with horizontally flipped images.
Re-size each gray-level image 60px height.
Contrast Normalization to random patches.
ZCA whitening with Ɛ=0.5.
Receptive field (patch) size 6x6 pixels
1 pixel stride with k=2400 words.
Final feature vector has 5x2400 dimensions.
[1] Shirish Krishnaj Shevade and S Sathiya Keerthi. A simple and efficient algorithm for gene selection using sparse logistic
regression. Bioinformatics,19(17):2246–2253, 2003.
[2] Simon Perkins, Kevin Lacker, and JFAMEs Theiler. Grafting: Fast, incremental feature selection by gradient descent in
function space. The Journal of Machine Learning Research, 3:1333–1356, 2003.
+
Datasets
PubFig83
Subset of PubFig with 83 celebrities
at least 100 images for each.
N. Pinto, Z. Stone, T. Zickler, and D. Cox, “Scaling up biologically-inspired computer vision: A case
study in unconstrained face recognition on facebook,” in Computer Vision and Pattern
Recognition Workshops (CVPRW), 2011.
+
Datasets
FAN-Large
EASY subset: faces larger than 60x70 px, 138 categories.
ALL: no constraint, 365 categories.
M. Ozcan, J. Luo, V. Ferrari, and B. Caputo, “A large-scale database of images and captions for
automatic face naming.,” in BMVC, pp. 1–11, 2011.
+ Results on PubFig83
N. Pinto, Z. Stone, T. Zickler, and D. Cox, “Scaling up biologically-inspired computer vision: A case study in
unconstrained face recognition on facebook,” in Computer Vision and Pattern Recognition Workshops
(CVPRW), 2011 IEEE Computer Society Conference on, pp. 35–42, IEEE, 2011
B. C. Becker and E. G. Ortiz, “Evaluating open-universe face identification on the web,” in Computer Vision
and Pattern Recognition Workshops (CVPRW), 2013 IEEE Conference on, pp. 904–911, IEEE, 2013.
No data refining, only our classification pipeline.
Models are trained on the training set of the given dataset
~5% improvement on State of Art
+
Evaluations
+ False versus true outlier elimination
+
Cross validation accuracies
+
Number of eliminations versus accuracy
+Models learned from weakly labeled set
 Baseline: all images collected for the query are used
 AME-M1 : Only M1 classifier which removes against global
negatives
 AME-SVM : with SVM as the final classifier
 AME-LR : the proposed method
S. Singh, A. Gupta, and A. A. Efros, “Unsupervised discovery of mid-level discriminative patches,”
in European Conference Computer Vision (ECCV), 2012.
+
Summary
 A method to build training sets from weakly-
labeled images
 Iterative pruning removes the outliers which are
the least confident instances
 High dimensional feature representation handles
the variations
+
TUBITAK 112E174
CHIST-ERA MUCKE
US Department of Defense, U. S. Army Research Office (W911NF-13-1-0277)
National Science Foundation Grant No. IIS-1251187
Thanks
+
Use annotated control set as a start point.
Fergus et. al. [1], OPTIMOL, Li and Fei-Fei [2]
We use fully autonomous framework.
Use Textual Captions
Berg and Forsyth [3]
We use only visual content
Discriminative image cues
Efros et al. [4] “Discriminative Patches”, Q. Li et al.[5]
We use single computer with faster and better results.
[1] Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from google’s image
search. In: Computer Vision, 2005. ICCV 2005
[2] Berg, T.L., Berg, A.C., Edwards, J., Maire, M., White, R., Teh, Y.W., Learned-Miller, E.G., Forsyth,
D.A.: NFAMEs and faces in the news. In: IEEE Conference on Computer Vision
Pattern Recognition (CVPR). Volume 2. (2004) 848–854
[3] Li, L.J., Fei-Fei, L.: Optimol: automatic online picture collection via incremental model learning.
International journal of computer vision 88(2) (2010) 147–168
[4] Li, Q., Wu, J., & Tu, Z. Harvesting Mid-level Visual Concepts from Large-scale Internet Images.

Contenu connexe

Tendances

auto-assistance system for visually impaired person
auto-assistance system for visually impaired personauto-assistance system for visually impaired person
auto-assistance system for visually impaired person
shahsamkit73
 
Face Detection techniques
Face Detection techniquesFace Detection techniques
Face Detection techniques
Abhineet Bhamra
 
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
Suvadip Shome
 
Face recognition using neural network
Face recognition using neural networkFace recognition using neural network
Face recognition using neural network
Indira Nayak
 
Moving object detection
Moving object detectionMoving object detection
Moving object detection
Manav Mittal
 

Tendances (20)

auto-assistance system for visually impaired person
auto-assistance system for visually impaired personauto-assistance system for visually impaired person
auto-assistance system for visually impaired person
 
Report
ReportReport
Report
 
Real-time Face Detection and Recognition
Real-time Face Detection and RecognitionReal-time Face Detection and Recognition
Real-time Face Detection and Recognition
 
Image recognition
Image recognitionImage recognition
Image recognition
 
Face Recognition Methods based on Convolutional Neural Networks
Face Recognition Methods based on Convolutional Neural NetworksFace Recognition Methods based on Convolutional Neural Networks
Face Recognition Methods based on Convolutional Neural Networks
 
Talk 8-Kevin-Imagej2
Talk 8-Kevin-Imagej2 Talk 8-Kevin-Imagej2
Talk 8-Kevin-Imagej2
 
Object detection
Object detectionObject detection
Object detection
 
Face Detection techniques
Face Detection techniquesFace Detection techniques
Face Detection techniques
 
IRJET- Face Counter using Matlab
IRJET-  	  Face Counter using MatlabIRJET-  	  Face Counter using Matlab
IRJET- Face Counter using Matlab
 
Modern face recognition with deep learning
Modern face recognition with deep learningModern face recognition with deep learning
Modern face recognition with deep learning
 
Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...
Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...
Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...
 
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
 
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream) Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
 
Deep learning on face recognition (use case, development and risk)
Deep learning on face recognition (use case, development and risk)Deep learning on face recognition (use case, development and risk)
Deep learning on face recognition (use case, development and risk)
 
Visual Object Tracking: review
Visual Object Tracking: reviewVisual Object Tracking: review
Visual Object Tracking: review
 
Image Search: Then and Now
Image Search: Then and NowImage Search: Then and Now
Image Search: Then and Now
 
Object tracking a survey
Object tracking a surveyObject tracking a survey
Object tracking a survey
 
Object Recognition
Object RecognitionObject Recognition
Object Recognition
 
Face recognition using neural network
Face recognition using neural networkFace recognition using neural network
Face recognition using neural network
 
Moving object detection
Moving object detectionMoving object detection
Moving object detection
 

En vedette

Fragment sculptural
Fragment sculpturalFragment sculptural
Fragment sculptural
sfast08
 
Performance Evaluation for Classifiers tutorial
Performance Evaluation for Classifiers tutorialPerformance Evaluation for Classifiers tutorial
Performance Evaluation for Classifiers tutorial
Bilkent University
 
Powerpoint presentation M.A. Thesis Defence
Powerpoint presentation M.A. Thesis DefencePowerpoint presentation M.A. Thesis Defence
Powerpoint presentation M.A. Thesis Defence
Catie Chase
 
Dissertation oral defense presentation
Dissertation   oral defense presentationDissertation   oral defense presentation
Dissertation oral defense presentation
Dr. Naomi Mangatu
 

En vedette (20)

Fragment sculptural
Fragment sculpturalFragment sculptural
Fragment sculptural
 
CVPR presentation
CVPR presentationCVPR presentation
CVPR presentation
 
Generacion 3.5 g
Generacion 3.5 gGeneracion 3.5 g
Generacion 3.5 g
 
2008 "An overview of Methods for analysis of Identifiability and Observabilit...
2008 "An overview of Methods for analysis of Identifiability and Observabilit...2008 "An overview of Methods for analysis of Identifiability and Observabilit...
2008 "An overview of Methods for analysis of Identifiability and Observabilit...
 
Prasheel
PrasheelPrasheel
Prasheel
 
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
 
Performance Evaluation for Classifiers tutorial
Performance Evaluation for Classifiers tutorialPerformance Evaluation for Classifiers tutorial
Performance Evaluation for Classifiers tutorial
 
Preparing for your viva voce dissertation defence.
Preparing for your viva voce dissertation defence.Preparing for your viva voce dissertation defence.
Preparing for your viva voce dissertation defence.
 
Research Proposal 5 - The Formal Meeting and Presentation
Research Proposal 5 - The Formal Meeting and PresentationResearch Proposal 5 - The Formal Meeting and Presentation
Research Proposal 5 - The Formal Meeting and Presentation
 
【2016.02】cvpaper.challenge2016
【2016.02】cvpaper.challenge2016【2016.02】cvpaper.challenge2016
【2016.02】cvpaper.challenge2016
 
Thesis Defense Presentation
Thesis Defense PresentationThesis Defense Presentation
Thesis Defense Presentation
 
Tips on how to defend your thesis
Tips on how to defend your thesisTips on how to defend your thesis
Tips on how to defend your thesis
 
Public speaking & oral presentation
Public speaking & oral presentationPublic speaking & oral presentation
Public speaking & oral presentation
 
Thesis powerpoint
Thesis powerpointThesis powerpoint
Thesis powerpoint
 
Proposal Defense Power Point
Proposal Defense Power PointProposal Defense Power Point
Proposal Defense Power Point
 
My Thesis Defense Presentation
My Thesis Defense PresentationMy Thesis Defense Presentation
My Thesis Defense Presentation
 
Powerpoint presentation M.A. Thesis Defence
Powerpoint presentation M.A. Thesis DefencePowerpoint presentation M.A. Thesis Defence
Powerpoint presentation M.A. Thesis Defence
 
Dissertation oral defense presentation
Dissertation   oral defense presentationDissertation   oral defense presentation
Dissertation oral defense presentation
 
ECCV 2016 速報
ECCV 2016 速報ECCV 2016 速報
ECCV 2016 速報
 
CVPR 2016 速報
CVPR 2016 速報CVPR 2016 速報
CVPR 2016 速報
 

Similaire à Fame cvpr

Gabriel Bianconi - Introduction to Face Processing with Computer Vision
Gabriel Bianconi - Introduction to Face Processing with Computer VisionGabriel Bianconi - Introduction to Face Processing with Computer Vision
Gabriel Bianconi - Introduction to Face Processing with Computer Vision
PyCon Odessa
 
Xin Yao: "What can evolutionary computation do for you?"
Xin Yao: "What can evolutionary computation do for you?"Xin Yao: "What can evolutionary computation do for you?"
Xin Yao: "What can evolutionary computation do for you?"
ieee_cis_cyprus
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
butest
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
butest
 
SSII2021 [SS2] Deepfake Generation and Detection – An Overview (ディープフェイクの生成と検出)
SSII2021 [SS2] Deepfake Generation and Detection – An Overview (ディープフェイクの生成と検出)SSII2021 [SS2] Deepfake Generation and Detection – An Overview (ディープフェイクの生成と検出)
SSII2021 [SS2] Deepfake Generation and Detection – An Overview (ディープフェイクの生成と検出)
SSII
 

Similaire à Fame cvpr (20)

Gabriel Bianconi - Introduction to Face Processing with Computer Vision
Gabriel Bianconi - Introduction to Face Processing with Computer VisionGabriel Bianconi - Introduction to Face Processing with Computer Vision
Gabriel Bianconi - Introduction to Face Processing with Computer Vision
 
Xin Yao: "What can evolutionary computation do for you?"
Xin Yao: "What can evolutionary computation do for you?"Xin Yao: "What can evolutionary computation do for you?"
Xin Yao: "What can evolutionary computation do for you?"
 
Face recognization using artificial nerual network
Face recognization using artificial nerual networkFace recognization using artificial nerual network
Face recognization using artificial nerual network
 
scene description
scene descriptionscene description
scene description
 
Image annotation - Segmentation & Annotation
Image annotation - Segmentation & AnnotationImage annotation - Segmentation & Annotation
Image annotation - Segmentation & Annotation
 
Introduction to the Artificial Intelligence and Computer Vision revolution
Introduction to the Artificial Intelligence and Computer Vision revolutionIntroduction to the Artificial Intelligence and Computer Vision revolution
Introduction to the Artificial Intelligence and Computer Vision revolution
 
TOP 5 Most View Article From Academia in 2019
TOP 5 Most View Article From Academia in 2019TOP 5 Most View Article From Academia in 2019
TOP 5 Most View Article From Academia in 2019
 
fuzzy LBP for face recognition ppt
fuzzy LBP for face recognition pptfuzzy LBP for face recognition ppt
fuzzy LBP for face recognition ppt
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
 
Learning Relations from Social Tagging Data
Learning Relations from Social Tagging DataLearning Relations from Social Tagging Data
Learning Relations from Social Tagging Data
 
SSII2021 [SS2] Deepfake Generation and Detection – An Overview (ディープフェイクの生成と検出)
SSII2021 [SS2] Deepfake Generation and Detection – An Overview (ディープフェイクの生成と検出)SSII2021 [SS2] Deepfake Generation and Detection – An Overview (ディープフェイクの生成と検出)
SSII2021 [SS2] Deepfake Generation and Detection – An Overview (ディープフェイクの生成と検出)
 
graziani_bias.pdf
graziani_bias.pdfgraziani_bias.pdf
graziani_bias.pdf
 
Human Being Character Analysis from Their Social Networking Profiles
Human Being Character Analysis from Their Social Networking ProfilesHuman Being Character Analysis from Their Social Networking Profiles
Human Being Character Analysis from Their Social Networking Profiles
 
Research in Deep Learning: A Perspective from NSF
Research in Deep Learning: A Perspective from NSFResearch in Deep Learning: A Perspective from NSF
Research in Deep Learning: A Perspective from NSF
 
Proposal presentation
Proposal presentationProposal presentation
Proposal presentation
 
Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues
Beyond Frontal Faces: Improving Person Recognition Using Multiple CuesBeyond Frontal Faces: Improving Person Recognition Using Multiple Cues
Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues
 
Effective community search_dami2015
Effective community search_dami2015Effective community search_dami2015
Effective community search_dami2015
 
Deep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and HypeDeep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and Hype
 
Fairness in Machine Learning
Fairness in Machine LearningFairness in Machine Learning
Fairness in Machine Learning
 

Dernier

Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Sérgio Sacani
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virus
NazaninKarimi6
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
PirithiRaju
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
Areesha Ahmad
 

Dernier (20)

Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate ProfessorThyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learning
 
Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
Kochi ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Kochi ESCORT SERVICE❤CALL GIRL
Kochi ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Kochi ESCORT SERVICE❤CALL GIRLKochi ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Kochi ESCORT SERVICE❤CALL GIRL
Kochi ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Kochi ESCORT SERVICE❤CALL GIRL
 
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts ServiceJustdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)
 
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxPSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virus
 
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
 
GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)
 
Introduction to Viruses
Introduction to VirusesIntroduction to Viruses
Introduction to Viruses
 
Grade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its FunctionsGrade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its Functions
 
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
 
Dubai Call Girls Beauty Face Teen O525547819 Call Girls Dubai Young
Dubai Call Girls Beauty Face Teen O525547819 Call Girls Dubai YoungDubai Call Girls Beauty Face Teen O525547819 Call Girls Dubai Young
Dubai Call Girls Beauty Face Teen O525547819 Call Girls Dubai Young
 
300003-World Science Day For Peace And Development.pptx
300003-World Science Day For Peace And Development.pptx300003-World Science Day For Peace And Development.pptx
300003-World Science Day For Peace And Development.pptx
 
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
 

Fame cvpr

  • 1. + FAME: Face Association through Model Evolution Pinar Duygulu (CMU, Hacettepe University) Eren Golge (Bilkent University)
  • 2. + Yale dataset: 10 subjects, 9 poses, 64 illuminations Labelled Faces in the wild 13323 Faces of 5749 celebrities PubFig dataset 60,000 images of 200 people Social Face Classification 4.4 million labeled faces from 4,030 people
  • 4. + Search web for faces of a query name
  • 5. + Use this set to learn models
  • 8. + Find category related images in the set of weakly labeled images
  • 9. +Our previous work: Densest component Most similar set of faces as a subgraph Assumption: The most similar subset of faces among the faces associated with a name will be the correct faces Drawback: Finds a single subset Ozkan, D., Duygulu, P., ”Interesting Faces: A Graph Based Approach for Finding People in News”, Pattern Recognition, 2010 Ozkan, D., Duygulu, P., ”A Graph Based Approach for Naming Faces in News Photos”, CVPR, 2006 Ozkan, D., Duygulu, P., ”Finding People Frequently Appearing in News”, CIVR, 2006
  • 10. + Our previous work: Concept Maps Grouping and outlier removal Golge, E., Duygulu, P., “Concept Maps: Mining Noisy Web Data for Concept Learning ”, accepted
  • 11. + Our previous work: Concept Maps Grouping and outlier removal Assumption: Faces of a single person can have sub- categories Outliers are different than the queried person Drawback: Eliminates strange looks not in groups as well
  • 12. + FAME Face Association through Model Evolution Capture discriminative and representative category images through iterative data cleansing Separate category instances versus random images. Agnostic data refining method against Irrelevancy. Evade Sub-Grouping using very high dimensional representations.
  • 13. + Overview of FAME First discern category candidates (CC) from random set (RS). Define category references(CR) inside CC . Second discern CR from CC. Define spurious instances (SI) against CR and eliminate. Re-Iterate
  • 14. + Step 1 Discerning category from random set Learn a linear model M1 betweencategory candidates CC and random set RS. Take the most confidently classified instances as the category references CR.
  • 15. + Step 2 Discerning category references from others Another model M2 between category references CR and other category candidates.
  • 16. + Step 3 Define spurious instances SI against category references CR. Eliminate SI.
  • 20. + High Dimensional Representation High dimensions help a category linearly separable from others despite of category modularity.
  • 21. + Feature learning Coates, Adam, Andrew Y. Ng, and Honglak Lee. "An analysis of single-layer networks in unsupervised feature learning." International Conference on Artificial Intelligence and Statistics. 2011.
  • 22. + Raw pixel LBP encoded outliers
  • 23. + Implementation details FAME Data refining : L1 Logistic Regression with Gauss-Seidel algorithm [1] Final Classifier: L1 Linear SVM with Grafting[2]. At each iteration 5 images are eliminated. Feature Learning Augment train data with horizontally flipped images. Re-size each gray-level image 60px height. Contrast Normalization to random patches. ZCA whitening with Ɛ=0.5. Receptive field (patch) size 6x6 pixels 1 pixel stride with k=2400 words. Final feature vector has 5x2400 dimensions. [1] Shirish Krishnaj Shevade and S Sathiya Keerthi. A simple and efficient algorithm for gene selection using sparse logistic regression. Bioinformatics,19(17):2246–2253, 2003. [2] Simon Perkins, Kevin Lacker, and JFAMEs Theiler. Grafting: Fast, incremental feature selection by gradient descent in function space. The Journal of Machine Learning Research, 3:1333–1356, 2003.
  • 24. + Datasets PubFig83 Subset of PubFig with 83 celebrities at least 100 images for each. N. Pinto, Z. Stone, T. Zickler, and D. Cox, “Scaling up biologically-inspired computer vision: A case study in unconstrained face recognition on facebook,” in Computer Vision and Pattern Recognition Workshops (CVPRW), 2011.
  • 25. + Datasets FAN-Large EASY subset: faces larger than 60x70 px, 138 categories. ALL: no constraint, 365 categories. M. Ozcan, J. Luo, V. Ferrari, and B. Caputo, “A large-scale database of images and captions for automatic face naming.,” in BMVC, pp. 1–11, 2011.
  • 26. + Results on PubFig83 N. Pinto, Z. Stone, T. Zickler, and D. Cox, “Scaling up biologically-inspired computer vision: A case study in unconstrained face recognition on facebook,” in Computer Vision and Pattern Recognition Workshops (CVPRW), 2011 IEEE Computer Society Conference on, pp. 35–42, IEEE, 2011 B. C. Becker and E. G. Ortiz, “Evaluating open-universe face identification on the web,” in Computer Vision and Pattern Recognition Workshops (CVPRW), 2013 IEEE Conference on, pp. 904–911, IEEE, 2013. No data refining, only our classification pipeline. Models are trained on the training set of the given dataset ~5% improvement on State of Art
  • 28. + False versus true outlier elimination
  • 30. + Number of eliminations versus accuracy
  • 31. +Models learned from weakly labeled set  Baseline: all images collected for the query are used  AME-M1 : Only M1 classifier which removes against global negatives  AME-SVM : with SVM as the final classifier  AME-LR : the proposed method S. Singh, A. Gupta, and A. A. Efros, “Unsupervised discovery of mid-level discriminative patches,” in European Conference Computer Vision (ECCV), 2012.
  • 32. + Summary  A method to build training sets from weakly- labeled images  Iterative pruning removes the outliers which are the least confident instances  High dimensional feature representation handles the variations
  • 33. + TUBITAK 112E174 CHIST-ERA MUCKE US Department of Defense, U. S. Army Research Office (W911NF-13-1-0277) National Science Foundation Grant No. IIS-1251187 Thanks
  • 34. + Use annotated control set as a start point. Fergus et. al. [1], OPTIMOL, Li and Fei-Fei [2] We use fully autonomous framework. Use Textual Captions Berg and Forsyth [3] We use only visual content Discriminative image cues Efros et al. [4] “Discriminative Patches”, Q. Li et al.[5] We use single computer with faster and better results. [1] Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from google’s image search. In: Computer Vision, 2005. ICCV 2005 [2] Berg, T.L., Berg, A.C., Edwards, J., Maire, M., White, R., Teh, Y.W., Learned-Miller, E.G., Forsyth, D.A.: NFAMEs and faces in the news. In: IEEE Conference on Computer Vision Pattern Recognition (CVPR). Volume 2. (2004) 848–854 [3] Li, L.J., Fei-Fei, L.: Optimol: automatic online picture collection via incremental model learning. International journal of computer vision 88(2) (2010) 147–168 [4] Li, Q., Wu, J., & Tu, Z. Harvesting Mid-level Visual Concepts from Large-scale Internet Images.