1 / 47

CVPR 2007 Minneapolis, Short Course, June 17

This course provides an overview of the challenges and methods in recognizing and categorizing objects in computer vision, including techniques for handling viewpoint variation, illumination, occlusion, scale, deformation, and background clutter. The course also explores different approaches to representation and learning, including generative, discriminative, and hybrid models.

htobey
Download Presentation

CVPR 2007 Minneapolis, Short Course, June 17

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. CVPR 2007 Minneapolis, Short Course, June 17 Recognizing and Learning Object Categories: Year 2007 Li Fei-Fei, Princeton Rob Fergus, MIT Antonio Torralba, MIT

  2. Agenda • Introduction • Bag-of-words models • Part-based models • Discriminative methods • Segmentation and recognition • Datasets & Conclusions

  3. material thing vision perceptible

  4. 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.

  5. Bruegel, 1564

  6. How many object categories are there? ~10,000 to 30,000 Biederman 1987

  7. So what does object recognition involve?

  8. Verification: is that a lamp?

  9. Detection: are there people?

  10. Identification: is that Potala Palace?

  11. Object categorization mountain tree building banner street lamp vendor people

  12. Scene and context categorization • outdoor • city • …

  13. Computational photography

  14. meters Ped Ped Car meters Assisted driving Pedestrian and car detection Lane detection • Collision warning systems with adaptive cruise control, • Lane departure warning systems, • Rear object detection systems,

  15. Improving online search Query: STREET Organizing photo collections

  16. Challenges 1: view point variation Michelangelo 1475-1564

  17. Challenges 2: illumination slide credit: S. Ullman

  18. Challenges 3: occlusion Magritte, 1957

  19. Challenges 4: scale

  20. Challenges 5: deformation Xu, Beihong 1943

  21. Challenges 6: background clutter Klimt, 1913

  22. History: single object recognition

  23. 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 • …

  24. Challenges 7: intra-class variation

  25. History: early object categorization

  26. 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

  27. ~10,000 to 30,000

  28. vs. • Bayes rule: posterior ratio likelihood ratio prior ratio Object categorization: the statistical viewpoint

  29. Object categorization: the statistical viewpoint posterior ratio likelihood ratio prior ratio • Discriminative methods model posterior • Generative methods model likelihood and prior

  30. Discriminative • Direct modeling of Decisionboundary Zebra Non-zebra

  31. Generative • Model and

  32. 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

  33. Representation • Generative / discriminative / hybrid

  34. Representation • Generative / discriminative / hybrid • Appearance only or location and appearance

  35. Representation • Generative / discriminative / hybrid • Appearance only or location and appearance • Invariances • View point • Illumination • Occlusion • Scale • Deformation • Clutter • etc.

  36. Representation • Generative / discriminative / hybrid • Appearance only or location and appearance • invariances • Part-based or global w/sub-window

  37. 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

  38. Learning • Unclear how to model categories, so we learn what distinguishes them rather than manually specify the difference -- hence current interest in machine learning

  39. Learning • 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

  40. Learning • 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 Contains a motorbike

  41. Learning • 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 )

  42. Learning • 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

  43. Learning • 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

  44. Recognition • Scale / orientation range to search over • Speed • Context

  45. Hoiem, Efros, Herbert, 2006

  46. OBJECTS INANIMATE ANIMALS PLANTS NATURAL MAN-MADE ….. VERTEBRATE MAMMALS BIRDS TAPIR BOAR GROUSE CAMERA

More Related