Your SlideShare is downloading. ×
Cvpr2007 object category recognition   p0 - introduction
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×

Saving this for later?

Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime - even offline.

Text the download link to your phone

Standard text messaging rates apply

Cvpr2007 object category recognition p0 - introduction

275
views

Published on

Published in: Education, Technology

0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
275
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
7
Comments
0
Likes
0
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide

Transcript

  • 1. Li Fei-Fei, Princeton Rob Fergus, MIT Antonio Torralba, MIT CVPR 2007 Minneapolis, Short Course, June 17 Recognizing and Learning Object Categories: Year 2007
  • 2. Agenda
    • Introduction
    • Bag-of-words models
    • Part-based models
    • Discriminative methods
    • Segmentation and recognition
    • Datasets & Conclusions
  • 3.  
  • 4. perceptible vision material thing
  • 5. Plato said…
    • Ordinary objects are classified together if they `participate' in the same abstract Form, such as the Form of a Human or the Form of Quartz.
    • Forms are proper subjects of philosophical investigation, for they have the highest degree of reality.
    • Ordinary objects, such as humans, trees, and stones, have a lower degree of reality than the Forms.
    • Fictions, shadows, and the like have a still lower degree of reality than ordinary objects and so are not proper subjects of philosophical enquiry.
  • 6. Bruegel, 1564
  • 7. How many object categories are there? ~10,000 to 30,000 Biederman 1987
  • 8. So what does object recognition involve?
  • 9. Verification: is that a lamp?
  • 10. Detection: are there people?
  • 11. Identification: is that Potala Palace?
  • 12. Object categorization mountain building tree banner vendor people street lamp
  • 13. Scene and context categorization
    • outdoor
    • city
  • 14. Computational photography
  • 15. Assisted driving Lane detection Pedestrian and car detection
    • Collision warning systems with adaptive cruise control,
    • Lane departure warning systems,
    • Rear object detection systems,
    meters meters Ped Ped Car
  • 16. Improving online search Query: STREET Organizing photo collections
  • 17. Challenges 1: view point variation Michelangelo 1475-1564
  • 18. Challenges 2: illumination slide credit: S. Ullman
  • 19. Challenges 3: occlusion Magritte, 1957
  • 20. Challenges 4: scale
  • 21. Challenges 5: deformation Xu, Beihong 1943
  • 22. Challenges 6: background clutter Klimt, 1913
  • 23. History: single object recognition
  • 24. History: single object recognition
    • Lowe, et al. 1999, 2003
    • Mahamud and Herbert, 2000
    • Ferrari, Tuytelaars, and Van Gool, 2004
    • Rothganger, Lazebnik, and Ponce, 2004
    • Moreels and Perona, 2005
  • 25. Challenges 7: intra-class variation
  • 26. History: early object categorization
  • 27.
    • Turk and Pentland, 1991
    • Belhumeur, Hespanha, & Kriegman, 1997
    • Schneiderman & Kanade 2004
    • Viola and Jones, 2000
    • Amit and Geman, 1999
    • LeCun et al. 1998
    • Belongie and Malik, 2002
    • Schneiderman & Kanade, 2004
    • Argawal and Roth, 2002
    • Poggio et al. 1993
  • 28. ~10,000 to 30,000
  • 29. Object categorization: the statistical viewpoint vs.
    • Bayes rule:
    posterior ratio likelihood ratio prior ratio
  • 30. Object categorization: the statistical viewpoint posterior ratio likelihood ratio prior ratio
    • Discriminative methods model posterior
    • Generative methods model likelihood and prior
  • 31. Discriminative
    • Direct modeling of
    Zebra Non-zebra Decision boundary
  • 32. Generative
    • Model and
    Middle  Low High Middle Low
  • 33. Three main issues
    • Representation
      • How to represent an object category
    • Learning
      • How to form the classifier, given training data
    • Recognition
      • How the classifier is to be used on novel data
  • 34. Representation
      • Generative / discriminative / hybrid
  • 35. Representation
      • Generative / discriminative / hybrid
      • Appearance only or location and appearance
  • 36. Representation
      • Generative / discriminative / hybrid
      • Appearance only or location and appearance
      • Invariances
        • View point
        • Illumination
        • Occlusion
        • Scale
        • Deformation
        • Clutter
        • etc.
  • 37. Representation
      • Generative / discriminative / hybrid
      • Appearance only or location and appearance
      • invariances
      • Part-based or global w/sub-window
  • 38. Representation
      • Generative / discriminative / hybrid
      • Appearance only or location and appearance
      • invariances
      • Parts or global w/sub-window
      • Use set of features or each pixel in image
  • 39.
      • Unclear how to model categories, so we learn what distinguishes them rather than manually specify the difference -- hence current interest in machine learning
    Learning
  • 40.
      • Unclear how to model categories, so we learn what distinguishes them rather than manually specify the difference -- hence current interest in machine learning)
      • Methods of training: generative vs. discriminative
    Learning
  • 41.
      • Unclear how to model categories, so we learn what distinguishes them rather than manually specify the difference -- hence current interest in machine learning)
      • What are you maximizing? Likelihood (Gen.) or performances on train/validation set (Disc.)
      • Level of supervision
        • Manual segmentation; bounding box; image labels; noisy labels
    Learning Contains a motorbike
  • 42.
      • Unclear how to model categories, so we learn what distinguishes them rather than manually specify the difference -- hence current interest in machine learning)
      • What are you maximizing? Likelihood (Gen.) or performances on train/validation set (Disc.)
      • Level of supervision
        • Manual segmentation; bounding box; image labels; noisy labels
      • Batch/incremental (on category and image level; user-feedback )
    Learning
  • 43.
      • Unclear how to model categories, so we learn what distinguishes them rather than manually specify the difference -- hence current interest in machine learning)
      • What are you maximizing? Likelihood (Gen.) or performances on train/validation set (Disc.)
      • Level of supervision
        • Manual segmentation; bounding box; image labels; noisy labels
      • Batch/incremental (on category and image level; user-feedback )
      • Training images:
        • Issue of overfitting
        • Negative images for discriminative methods Priors
    Learning
  • 44.
      • Unclear how to model categories, so we learn what distinguishes them rather than manually specify the difference -- hence current interest in machine learning)
      • What are you maximizing? Likelihood (Gen.) or performances on train/validation set (Disc.)
      • Level of supervision
        • Manual segmentation; bounding box; image labels; noisy labels
      • Batch/incremental (on category and image level; user-feedback )
      • Training images:
        • Issue of overfitting
        • Negative images for discriminative methods
      • Priors
    Learning
  • 45.
      • Scale / orientation range to search over
      • Speed
      • Context
    Recognition
  • 46. Hoiem, Efros, Herbert, 2006
  • 47. OBJECTS ANIMALS INANIMATE PLANTS MAN-MADE NATURAL VERTEBRATE … .. MAMMALS BIRDS GROUSE BOAR TAPIR CAMERA