1. Object class recognition using unsupervised scale-invariant learning Rob Fergus Pietro Perona Andrew Zisserman Oxford University California Institute of Technology

2. 1 Representation 2 Learning 3 Recognition Overview Task: Recognition of object categories 3 main issues:

3. Some object categories Learn from just examples Difficulties: fSize variation fBackground clutter fOcclusion fIntra-class variation

4. Model: constellation of Parts Fischler & Elschlager, 1973  Yuille, ‘ 91  Brunelli & Poggio, ‘ 93  Lades, v.d. Malsburg et al. ‘ 93  Cootes, Lanitis, Taylor et al. ‘ 95  Amit & Geman, ‘ 95, ‘ 99  Perona et al. ‘ 95, ‘ 96, ’ 98, ‘ 00

5. Foreground model Gaussian shape pdf Pp oisson (N| ) p(x)=A -1 (uniform) Clutter pdf Poission pdf on # detections Uniform shape pdf Prob. of detection Gaussian part appearance pdf Generative probabilistic model p(A)=  parts G(A part |c part,V part ) Clutter model Gaussian relative scale pdf Log(scale) Gaussian appearance pdf 0.80.750.9 Uniform relative scale pdf Log(scale)

6. Interest Operator • Kadir and Brady's interest operator. • Finds maxima in entropy over scale and location

7. Representation of appearance 11x11 patch c1c1 c2c2 Normalize Projection onto PCA basis c 15

8. Experimental procedure Two series of experiments: Datasets: • Motorbikes, Faces, Spotted cats, Airplanes, Cars from behind and side • Between 200 and 800 images in size Training • 50% images • No identifcation of object within image 1 Scale variant (using pre-scaled images) 2 Scale invariant Testing • 50% images • Simple object present/absent test • ROC equal error rate computed, using background set of images

9. Motorbikes

12. Equal error rate: 7.5%

13. Background images

14. Frontal faces Equal error rate: 4.6%

15. Airplanes Equal error rate: 9.8%

16. Scale-invariant Spotted cats Equal error rate: 10.0%

17. Scale-invariant cars Equal error rate: 9.7%

18. Robustness of algorithm

19. ROC equal error rates Pre-scaled data (identical settings): Scale-invariant learning and recognition:

21. Scale-invariant cars