SlideShare a Scribd company logo
1 of 26
Learning on the Fly:
               Rapid Adaptation to the Image

                         Erik Learned-Miller
                         with Vidit Jain, Gary Huang,
                     Laura Sevilla Lara, Manju Narayana,
                                  Ben Mears




Computer Science Department
“Traditional” machine learning
   Learning happens from large data sets
       • With labels: supervised learning
       • Without labels: unsupervised learning
       • Mixed labels: semi-supervised learning,
                         transfer learning,
                         learning from one (labeled) example,
                         self-taught learning,
                         domain adaptation




Learning on the Fly                                             2
Learning on the Fly
   Given:
       • A learning machine trained with traditional methods
       • a single test image (no labels)
   Learn from the test image!




Learning on the Fly                                            3
Learning on the Fly
   Given:
       • A learning machine trained with traditional methods
       • a single test image (no labels)
   Learn from the test image!
       • Domain adaptation where the “domain” is the new
         image
          • No covariate shift assumption.
          • No new labels




Learning on the Fly                                            4
An Example in Computer Vision
   Parsing Images of Architectural Scenes
       Berg, Grabler, and Malik ICCV 2007.
       • Detect easy or “canonical” stuff.
       • Use easily detected stuff to bootstrap models of harder
         stuff.




Learning on the Fly                                                5
Claim
   This is so easy and routine for humans that it’s
    hard to realize we’re doing it.
       • Another example…




Learning on the Fly                                    6
Learning on the fly…




Learning on the Fly     7
Learning on the fly…




Learning on the Fly     8
Learning on the fly…




Learning on the Fly     9
What about traditional methods…
   Hidden Markov Model for text recognition:
       • Appearance model for characters
       • Language model for labels
       • Use Viterbi to do joint inference




Learning on the Fly                             10
What about traditional methods…
   Hidden Markov Model for text recognition:
       • Appearance model for characters
       • Language model for labels
       • Use Viterbi to do joint inference
   DOESN’T WORK!

      Prob(      |Label=A) cannot be well estimated,
      fouling up the whole process.




Learning on the Fly                                    11
Lessons
   We must assess when our models are broken,
    and use other methods to proceed….
       • Current methods of inference assume probabilities are
         correct!
          • “In vision, probabilities are often junk.”
          • Related to similarity becoming meaningless beyond a
            certain distance.




Learning on the Fly                                               12
2 Examples
   Face detection (CVPR 2011)
   OCR (CVPR 2010)




Learning on the Fly              13
Preview of results: Finding false negatives

           Viola-Jones     Learning on the Fly




Learning on the Fly                              14
Eliminating false positives

           Viola-Jones     Learning on the Fly




Learning on the Fly                              15
Eliminating false positives

           Viola-Jones     Learning on the Fly




Learning on the Fly                              16
Run a pre-existing detector...




Learning on the Fly               17
Run a pre-existing detector...

                                   Key

                                  Face


                                  Non-face


                                  Close to
                                  boundary


Learning on the Fly                          18
Gaussian Process Regression
                                  learn smooth mapping
                                  from appearance to score



                          negative                  positive



                      apply mapping to borderline
                      patches



Learning on the Fly                                     19
Major Performance Gains




Learning on the Fly        20
Comments
   No need to retrain original detector
       • It wouldn’t change anyway!
   No need to access original training data
   Still runs in real-time
   GP regression is done for every new image.




Learning on the Fly                              21
Noisy Document




             Initial Transcription
                      We fine herefore t
                      linearly rolatcd to the
                      when this is calculated
                      equilibriurn. In short,
                      on the null-hypothesis:
Learning on the Fly                             22
Premise
   We would like to fine confident words
       to build a document-specific model,
       but it is difficult to estimate Prob(error).
   However, we can bound Prob(error).
   Now, select words with
       • Prob(error)<epsilon.




Learning on the Fly                                   23
“Clean Sets”




Learning on the Fly   24
Document specific OCR
   Extract clean sets (error bounded sets)
   Build document-specific models from clean set
    characters
   Reclassify other characters in document
       • 30% error reduction on 56 documents.




Learning on the Fly                                 25
Summary
   Many applications of learning on the fly.
   Adaptation and bootstrapping new models is
    more common in human learning than is
    generally believed.
   Starting to answer the question: “How can we do
    domain adaptation from a single image?”




Learning on the Fly                                   26

More Related Content

More from zukun

Siwei lyu: natural image statistics
Siwei lyu: natural image statisticsSiwei lyu: natural image statistics
Siwei lyu: natural image statisticszukun
 
Lecture9 camera calibration
Lecture9 camera calibrationLecture9 camera calibration
Lecture9 camera calibrationzukun
 
Brunelli 2008: template matching techniques in computer vision
Brunelli 2008: template matching techniques in computer visionBrunelli 2008: template matching techniques in computer vision
Brunelli 2008: template matching techniques in computer visionzukun
 
Modern features-part-4-evaluation
Modern features-part-4-evaluationModern features-part-4-evaluation
Modern features-part-4-evaluationzukun
 
Modern features-part-3-software
Modern features-part-3-softwareModern features-part-3-software
Modern features-part-3-softwarezukun
 
Modern features-part-2-descriptors
Modern features-part-2-descriptorsModern features-part-2-descriptors
Modern features-part-2-descriptorszukun
 
Modern features-part-1-detectors
Modern features-part-1-detectorsModern features-part-1-detectors
Modern features-part-1-detectorszukun
 
Modern features-part-0-intro
Modern features-part-0-introModern features-part-0-intro
Modern features-part-0-introzukun
 
Lecture 02 internet video search
Lecture 02 internet video searchLecture 02 internet video search
Lecture 02 internet video searchzukun
 
Lecture 01 internet video search
Lecture 01 internet video searchLecture 01 internet video search
Lecture 01 internet video searchzukun
 
Lecture 03 internet video search
Lecture 03 internet video searchLecture 03 internet video search
Lecture 03 internet video searchzukun
 
Icml2012 tutorial representation_learning
Icml2012 tutorial representation_learningIcml2012 tutorial representation_learning
Icml2012 tutorial representation_learningzukun
 
Advances in discrete energy minimisation for computer vision
Advances in discrete energy minimisation for computer visionAdvances in discrete energy minimisation for computer vision
Advances in discrete energy minimisation for computer visionzukun
 
Gephi tutorial: quick start
Gephi tutorial: quick startGephi tutorial: quick start
Gephi tutorial: quick startzukun
 
EM algorithm and its application in probabilistic latent semantic analysis
EM algorithm and its application in probabilistic latent semantic analysisEM algorithm and its application in probabilistic latent semantic analysis
EM algorithm and its application in probabilistic latent semantic analysiszukun
 
Object recognition with pictorial structures
Object recognition with pictorial structuresObject recognition with pictorial structures
Object recognition with pictorial structureszukun
 
Iccv2011 learning spatiotemporal graphs of human activities
Iccv2011 learning spatiotemporal graphs of human activities Iccv2011 learning spatiotemporal graphs of human activities
Iccv2011 learning spatiotemporal graphs of human activities zukun
 
Icml2012 learning hierarchies of invariant features
Icml2012 learning hierarchies of invariant featuresIcml2012 learning hierarchies of invariant features
Icml2012 learning hierarchies of invariant featureszukun
 
ECCV2010: Modeling Temporal Structure of Decomposable Motion Segments for Act...
ECCV2010: Modeling Temporal Structure of Decomposable Motion Segments for Act...ECCV2010: Modeling Temporal Structure of Decomposable Motion Segments for Act...
ECCV2010: Modeling Temporal Structure of Decomposable Motion Segments for Act...zukun
 
Quoc le tera-scale deep learning
Quoc le   tera-scale deep learningQuoc le   tera-scale deep learning
Quoc le tera-scale deep learningzukun
 

More from zukun (20)

Siwei lyu: natural image statistics
Siwei lyu: natural image statisticsSiwei lyu: natural image statistics
Siwei lyu: natural image statistics
 
Lecture9 camera calibration
Lecture9 camera calibrationLecture9 camera calibration
Lecture9 camera calibration
 
Brunelli 2008: template matching techniques in computer vision
Brunelli 2008: template matching techniques in computer visionBrunelli 2008: template matching techniques in computer vision
Brunelli 2008: template matching techniques in computer vision
 
Modern features-part-4-evaluation
Modern features-part-4-evaluationModern features-part-4-evaluation
Modern features-part-4-evaluation
 
Modern features-part-3-software
Modern features-part-3-softwareModern features-part-3-software
Modern features-part-3-software
 
Modern features-part-2-descriptors
Modern features-part-2-descriptorsModern features-part-2-descriptors
Modern features-part-2-descriptors
 
Modern features-part-1-detectors
Modern features-part-1-detectorsModern features-part-1-detectors
Modern features-part-1-detectors
 
Modern features-part-0-intro
Modern features-part-0-introModern features-part-0-intro
Modern features-part-0-intro
 
Lecture 02 internet video search
Lecture 02 internet video searchLecture 02 internet video search
Lecture 02 internet video search
 
Lecture 01 internet video search
Lecture 01 internet video searchLecture 01 internet video search
Lecture 01 internet video search
 
Lecture 03 internet video search
Lecture 03 internet video searchLecture 03 internet video search
Lecture 03 internet video search
 
Icml2012 tutorial representation_learning
Icml2012 tutorial representation_learningIcml2012 tutorial representation_learning
Icml2012 tutorial representation_learning
 
Advances in discrete energy minimisation for computer vision
Advances in discrete energy minimisation for computer visionAdvances in discrete energy minimisation for computer vision
Advances in discrete energy minimisation for computer vision
 
Gephi tutorial: quick start
Gephi tutorial: quick startGephi tutorial: quick start
Gephi tutorial: quick start
 
EM algorithm and its application in probabilistic latent semantic analysis
EM algorithm and its application in probabilistic latent semantic analysisEM algorithm and its application in probabilistic latent semantic analysis
EM algorithm and its application in probabilistic latent semantic analysis
 
Object recognition with pictorial structures
Object recognition with pictorial structuresObject recognition with pictorial structures
Object recognition with pictorial structures
 
Iccv2011 learning spatiotemporal graphs of human activities
Iccv2011 learning spatiotemporal graphs of human activities Iccv2011 learning spatiotemporal graphs of human activities
Iccv2011 learning spatiotemporal graphs of human activities
 
Icml2012 learning hierarchies of invariant features
Icml2012 learning hierarchies of invariant featuresIcml2012 learning hierarchies of invariant features
Icml2012 learning hierarchies of invariant features
 
ECCV2010: Modeling Temporal Structure of Decomposable Motion Segments for Act...
ECCV2010: Modeling Temporal Structure of Decomposable Motion Segments for Act...ECCV2010: Modeling Temporal Structure of Decomposable Motion Segments for Act...
ECCV2010: Modeling Temporal Structure of Decomposable Motion Segments for Act...
 
Quoc le tera-scale deep learning
Quoc le   tera-scale deep learningQuoc le   tera-scale deep learning
Quoc le tera-scale deep learning
 

Recently uploaded

TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxLoriGlavin3
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionDilum Bandara
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .Alan Dix
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxLoriGlavin3
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningLars Bell
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
unit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxunit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxBkGupta21
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 

Recently uploaded (20)

TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An Introduction
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine Tuning
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
unit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxunit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptx
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 

Fcv learn learned-miller

  • 1. Learning on the Fly: Rapid Adaptation to the Image Erik Learned-Miller with Vidit Jain, Gary Huang, Laura Sevilla Lara, Manju Narayana, Ben Mears Computer Science Department
  • 2. “Traditional” machine learning  Learning happens from large data sets • With labels: supervised learning • Without labels: unsupervised learning • Mixed labels: semi-supervised learning, transfer learning, learning from one (labeled) example, self-taught learning, domain adaptation Learning on the Fly 2
  • 3. Learning on the Fly  Given: • A learning machine trained with traditional methods • a single test image (no labels)  Learn from the test image! Learning on the Fly 3
  • 4. Learning on the Fly  Given: • A learning machine trained with traditional methods • a single test image (no labels)  Learn from the test image! • Domain adaptation where the “domain” is the new image • No covariate shift assumption. • No new labels Learning on the Fly 4
  • 5. An Example in Computer Vision  Parsing Images of Architectural Scenes Berg, Grabler, and Malik ICCV 2007. • Detect easy or “canonical” stuff. • Use easily detected stuff to bootstrap models of harder stuff. Learning on the Fly 5
  • 6. Claim  This is so easy and routine for humans that it’s hard to realize we’re doing it. • Another example… Learning on the Fly 6
  • 7. Learning on the fly… Learning on the Fly 7
  • 8. Learning on the fly… Learning on the Fly 8
  • 9. Learning on the fly… Learning on the Fly 9
  • 10. What about traditional methods…  Hidden Markov Model for text recognition: • Appearance model for characters • Language model for labels • Use Viterbi to do joint inference Learning on the Fly 10
  • 11. What about traditional methods…  Hidden Markov Model for text recognition: • Appearance model for characters • Language model for labels • Use Viterbi to do joint inference  DOESN’T WORK! Prob( |Label=A) cannot be well estimated, fouling up the whole process. Learning on the Fly 11
  • 12. Lessons  We must assess when our models are broken, and use other methods to proceed…. • Current methods of inference assume probabilities are correct! • “In vision, probabilities are often junk.” • Related to similarity becoming meaningless beyond a certain distance. Learning on the Fly 12
  • 13. 2 Examples  Face detection (CVPR 2011)  OCR (CVPR 2010) Learning on the Fly 13
  • 14. Preview of results: Finding false negatives Viola-Jones Learning on the Fly Learning on the Fly 14
  • 15. Eliminating false positives Viola-Jones Learning on the Fly Learning on the Fly 15
  • 16. Eliminating false positives Viola-Jones Learning on the Fly Learning on the Fly 16
  • 17. Run a pre-existing detector... Learning on the Fly 17
  • 18. Run a pre-existing detector... Key Face Non-face Close to boundary Learning on the Fly 18
  • 19. Gaussian Process Regression learn smooth mapping from appearance to score negative positive apply mapping to borderline patches Learning on the Fly 19
  • 21. Comments  No need to retrain original detector • It wouldn’t change anyway!  No need to access original training data  Still runs in real-time  GP regression is done for every new image. Learning on the Fly 21
  • 22. Noisy Document Initial Transcription We fine herefore t linearly rolatcd to the when this is calculated equilibriurn. In short, on the null-hypothesis: Learning on the Fly 22
  • 23. Premise  We would like to fine confident words to build a document-specific model, but it is difficult to estimate Prob(error).  However, we can bound Prob(error).  Now, select words with • Prob(error)<epsilon. Learning on the Fly 23
  • 25. Document specific OCR  Extract clean sets (error bounded sets)  Build document-specific models from clean set characters  Reclassify other characters in document • 30% error reduction on 56 documents. Learning on the Fly 25
  • 26. Summary  Many applications of learning on the fly.  Adaptation and bootstrapping new models is more common in human learning than is generally believed.  Starting to answer the question: “How can we do domain adaptation from a single image?” Learning on the Fly 26