1 / 32

Why Categorize in Computer Vision?

Why Categorize in Computer Vision?. Why Use Categories?. People love categories!. Why Use Categories?. What if we didn’t have categories?. Humuhumunukunukuapua'a – “fish that grunts like a pig”. Why Use Categories?. Our minds work very intimately with categories

saman
Télécharger la présentation

Why Categorize in Computer Vision?

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. Why Categorize in Computer Vision?

  2. Why Use Categories? People love categories!

  3. Why Use Categories? What if we didn’t have categories? Humuhumunukunukuapua'a – “fish that grunts like a pig”

  4. Why Use Categories? Our minds work very intimately with categories • Every common noun in English is a category • Proper nouns name object instances • “this,” “that,” “the,” “my,” “yours,” etc. refer to object instances anonymously

  5. The Categorization Problem

  6. The Categorization Problem Categorization/Classification: Given a set of pre-defined categories, “bin” this image Does not necessarily require object detection Vertical Dimension: • General: “Animal” • Basic: “Bird” • Specific: “Robin”

  7. The Categorization Problem What kinds of categorization are computers good at? • Basic -- especially when using context clues • Specific -- due to low intra-class variation

  8. The Categorization Problem Bad at? • General, due to high intra-class variation and a lack of visual cues

  9. The Categorization Problem Bad at? • Categories defined by non-visual characteristics (like chairs)

  10. Summary • Semantic categories allow humans to convey a large amount of information concisely • We want computers to be able to do the same • What work has been done on this problem? Has it been successful?

  11. Uses of Categorization

  12. Two Examples • Using Context in Categorization • Fine-Grain Object Classification

  13. Caltech 101 (2003) • Dataset for basic-level categorization • Objects from 101 classes • Famously difficult

  14. Categorization with Context Goal: Resolve ambiguity between similar-looking objects of different classes using the semantic context of an object Rabinovich et al. (UC San Diego): Objects in Context First paper to attempt to use context at the object level PASCAL 2007 dataset

  15. Categorization with Context

  16. Categorization with Context Approach • Segment image to preserve some spatial data • Perform Bag-of-Features to give an initial ranked list of labels for each segment • Use a Conditional Random Field (CRF) framework to find agreement between segment labels

  17. Categorization with Context

  18. Bag-of-Features with Segmentation Labeling Segments: Confidence:

  19. Conditional Random Field Way to assign joint probabilities to elements without considering every possible combination in the training set

  20. Conditional Random Field Idea • Given set of segments S, set of labels C • Want to find p(C | S) without knowing p(S) • Associate a special graph with C that obeys the “Markov Property” (uses S) • The ordered pair (S, C) is a CRF conditioned on S

  21. Conditional Random Field

  22. Results

  23. Results False correction

  24. Fine-Grain Classification

  25. Fine-Grain Image Categorization Challenge: need good classifiers that capture detail well

  26. Fine-Grain Image Categorization Yao et al. (Stanford): Combining Randomization and Discrimination for Fine-Grained Image Categorization Approach Random forest with discriminative classifiers This is a kind of machine learning framework that allows us to handle the fine detail in this problem.

  27. Fine-Grain Image Categorization

  28. Random Discriminative Tree Approach • For each tree node, train an SVM classifier for a randomly sampled image region • At each node, make a yes-or-no decision • Uses grayscale SIFT descriptors

  29. Random Discriminative Tree

  30. Results

  31. Conclusion • Semantic categories allow humans to convey a large amount of information concisely • Categorization has been used for basic-level object detection and scene recognition • Fine-grain categorization can provide us with expert-level classification of objects • Not all categories are defined by visual characteristics!

  32. Questions?

More Related