1. Bag-of-features models

2. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures, it is the identity of the textons, not their spatial arrangement, that matters Julesz, 1981; Cula & Dana, 2001; Leung & Malik 2001; Mori, Belongie & Malik, 2001; Schmid 2001; Varma & Zisserman, 2002, 2003; Lazebnik, Schmid & Ponce, 2003

3. Origin 1: Texture recognition Universal texton dictionary histogram Julesz, 1981; Cula & Dana, 2001; Leung & Malik 2001; Mori, Belongie & Malik, 2001; Schmid 2001; Varma & Zisserman, 2002, 2003; Lazebnik, Schmid & Ponce, 2003

4. Origin 2: Bag-of-words models Orderless document representation: frequencies of words from a dictionary Salton & McGill (1983)

5. Origin 2: Bag-of-words models US Presidential Speeches Tag Cloud http://chir.ag/phernalia/preztags/ Orderless document representation: frequencies of words from a dictionary Salton & McGill (1983)

6. Origin 2: Bag-of-words models US Presidential Speeches Tag Cloud http://chir.ag/phernalia/preztags/ Orderless document representation: frequencies of words from a dictionary Salton & McGill (1983)

7. Origin 2: Bag-of-words models US Presidential Speeches Tag Cloud http://chir.ag/phernalia/preztags/ Orderless document representation: frequencies of words from a dictionary Salton & McGill (1983)

8. 1.Extract features 2.Learn “visual vocabulary” 3.Quantize features using visual vocabulary 4.Represent images by frequencies of “visual words” Bag-of-features steps

9. 1. Feature extraction Regular grid or interest regions

10. Normalize patch Detect patches Compute descriptor Slide credit: Josef Sivic 1. Feature extraction

11. … Slide credit: Josef Sivic

12. 2. Learning the visual vocabulary … Slide credit: Josef Sivic

13. 2. Learning the visual vocabulary Clustering … Slide credit: Josef Sivic

14. 2. Learning the visual vocabulary Clustering … Slide credit: Josef Sivic Visual vocabulary

15. K-means clustering Want to minimize sum of squared Euclidean distances between points x i and their nearest cluster centers m k Algorithm: Randomly initialize K cluster centers Iterate until convergence: Assign each data point to the nearest center Recompute each cluster center as the mean of all points assigned to it

16. Clustering and vector quantization Clustering is a common method for learning a visual vocabulary or codebook Unsupervised learning process Each cluster center produced by k-means becomes a codevector Codebook can be learned on separate training set Provided the training set is sufficiently representative, the codebook will be “universal” The codebook is used for quantizing features A vector quantizer takes a feature vector and maps it to the index of the nearest codevector in a codebook Codebook = visual vocabulary Codevector = visual word

17. Example codebook … Source: B. Leibe Appearance codebook

18. Another codebook Appearance codebook … … … … … Source: B. Leibe

19. Yet another codebook Fei-Fei et al. 2005

20. Visual vocabularies: Issues How to choose vocabulary size? Too small: visual words not representative of all patches Too large: quantization artifacts, overfitting Computational efficiency Vocabulary trees (Nister & Stewenius, 2006)

21. Spatial pyramid representation Extension of a bag of features Locally orderless representation at several levels of resolution level 0 Lazebnik, Schmid & Ponce (CVPR 2006)

22. Spatial pyramid representation Extension of a bag of features Locally orderless representation at several levels of resolution level 0 level 1 Lazebnik, Schmid & Ponce (CVPR 2006)

23. Spatial pyramid representation level 0 level 1 level 2 Extension of a bag of features Locally orderless representation at several levels of resolution Lazebnik, Schmid & Ponce (CVPR 2006)

24. Scene category dataset Multi-class classification results (100 training images per class)

25. Caltech101 dataset http://www.vision.caltech.edu/Image_Datasets/Caltech101/Caltech101.html Multi-class classification results (30 training images per class)

26. Bags of features for action recognition Juan Carlos Niebles, Hongcheng Wang and Li Fei-Fei, Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words, IJCV 2008.Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words Space-time interest points

27. Bags of features for action recognition Juan Carlos Niebles, Hongcheng Wang and Li Fei-Fei, Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words, IJCV 2008.Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words

28. Beyond bags of features: Part-based models Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba

29. Implicit shape models Visual codebook is used to index votes for object position B. Leibe, A. Leonardis, and B. Schiele, Combined Object Categorization and Segmentation with an Implicit Shape Model, ECCV Workshop on Statistical Learning in Computer Vision 2004Combined Object Categorization and Segmentation with an Implicit Shape Model training image annotated with object localization info visual codeword with displacement vectors

30. Implicit shape models Visual codebook is used to index votes for object position B. Leibe, A. Leonardis, and B. Schiele, Combined Object Categorization and Segmentation with an Implicit Shape Model, ECCV Workshop on Statistical Learning in Computer Vision 2004Combined Object Categorization and Segmentation with an Implicit Shape Model test image

31. Implicit shape models: Training 1.Build codebook of patches around extracted interest points using clustering

32. Implicit shape models: Training 1.Build codebook of patches around extracted interest points using clustering 2.Map the patch around each interest point to closest codebook entry

33. Implicit shape models: Training 1.Build codebook of patches around extracted interest points using clustering 2.Map the patch around each interest point to closest codebook entry 3.For each codebook entry, store all positions it was found, relative to object center

34. Implicit shape models: Testing 1.Given test image, extract patches, match to codebook entry 2.Cast votes for possible positions of object center 3.Search for maxima in voting space 4.Extract weighted segmentation mask based on stored masks for the codebook occurrences

35. Source: B. Leibe Original image Example: Results on Cows

36. Interest points Example: Results on Cows Source: B. Leibe

37. Example: Results on Cows Matched patches Source: B. Leibe

38. Example: Results on Cows Probabilistic votes Source: B. Leibe

39. Example: Results on Cows Hypothesis 1 Source: B. Leibe

40. Example: Results on Cows Hypothesis 2 Source: B. Leibe

41. Example: Results on Cows Hypothesis 3 Source: B. Leibe

42. Additional examples B. Leibe, A. Leonardis, and B. Schiele, Robust Object Detection with Interleaved Categorization and Segmentation, IJCV 77 (1-3), pp. 259-289, 2008.Robust Object Detection with Interleaved Categorization and Segmentation