Download presentation
Presentation is loading. Please wait.
1
Unsupervised learning of models for recognition
P. Perona, M. Weber, and M. Welling California Institute of Technology, Universita’ di Padova & University College, London Vision Sciences 2001
2
Meet the xyz
3
Meet the xyz
4
Meet the xyz
5
Meet the xyz
6
Meet the xyz
7
Meet the xyz
8
Spot the xyz
9
Spot the xyz
10
Spot the xyz
11
Spot the xyz
12
Spot the xyz
13
Spot the xyz
14
Main issues: Representation Recognition Learning ARVO 1999
15
Variability within a category
Intrinsic Deformation
16
Model: constellation of Parts
Tanaka et al., 1993 Fischler & Elschlager, 1973 Yuille, ‘91 Brunelli & Poggio, ‘93 Lades, v.d. Malsburg et al. ‘93 Lanitis, Taylor et al. ‘95 Amit & Geman, ‘95, ‘99 Burl, Leung, Perona ‘95, ‘96, ‘98 Perrett & Oram, 1993
17
A Deformations
18
A B Deformations
19
A B Deformations C
20
A B Deformations C D
21
Presence / Absence of Features
occlusion
22
Background clutter
23
Generative probabilistic model
Model (Parameters) Foreground pdf Prob. of Detection Background pdf 0.8 0.9 Prob. of N detect. Pdf of location pPoisson(N1|1) 0.9 pPoisson(N2|2) p(x)=A-1 (uniform) Final Image pPoisson(N3|3) e.g. p(x)=G(x| , ) Example 1. Object Part Positions 2. Part Absence 3a. N false detect 3b. Position f. detect N1 N2 N3
24
Optimal observer detection
+ + + + + + + + + + + + + + + + + + + Likelihood ratio test [From Burl, Weber & Perona - CVPR 1996]
25
Unsupervised learning : Frontal Views of Faces
200 Images (100 training, 100 testing) 30 people, different for training and testing
26
Unsupervised detector training - 1
Highly textured points are detected with Förstner’s interest operator. can detect corner points and circular patterns produces more than 10,000 patterns
27
Unsupervised detector training - 2
“Pattern Space” (100+ dimensions)
28
Parts in model
29
Parameter Estimation Apply detectors….. Obtain training images, suppose we had some detectors
30
optimize for representation
Parameter Estimation Chicken-and-egg problem with shape and correspondence. Use EM. Signal? Clutter? Correspondence? optimize for representation (ML on generative models)
31
ML using EM 1. Current estimate
2. Assign probabilities to constellations (E) Large P ... pdf Image 1 Image 2 Image i Small P 3. Use probabilities as weights to reestimate parameters (M). Example: Large P x + Small P x + … = new estimate of
32
Learned face model Preselected Parts Test Error: 6% (4 Parts)
Parts in Model Model Foreground pdf Sample Detection
33
Face images (~90% correct classific.)
34
Background images
35
Rear Views of Cars 200 Images (100 training, 100 testing)
Only one image per car High-pass filtered
36
Learned Model Preselected Parts Test Error: 13% (5 Parts)
Parts in Model Model Foreground pdf Sample Detection
37
Detections of Cars (~87% correct classification)
38
Background Images
39
Dilbert 125 examples 77 examples vs.
40
Dilbert Model Model Foreground pdf Preselected Parts Parts in Model
Sample Detection Test Error: 15% (4 Parts)
41
Main points Probabilistic constellation models (ARVO ’99)
Maximum Likelihood Learning Unsupervised learning of object categories in clutter Works well on faces, heads, cars, Dilbert, leaves, handwriting
42
Pietro Perona, Markus Weber, Max Welling References
FG 2000 (viewpoint invariance) ECCV 2000 (EM algor. for unsupervised learning) CVPR 2000 (learning of multiple classes) available from: (click on `publications’) Funded by: National Science Foundation Sloan Foundation Pietro Perona, Markus Weber, Max Welling
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.