cvpr2010: semi-supervised learning in vision: part 1: introduction
DESCRIPTION
TRANSCRIPT
![Page 1: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/1.jpg)
ICG
Professor Horst Cerjak, 19.12.20051
Horst Bischof SSL CVPR Tutorial
CVPR 2010 Tutorial Semi-Supervised Learning in
Vision
Inst. for Computer Graphics and VisionGraz University of Technology
A, Saffari, Ch. Leistner, H. Bischof
http://www.icg.tugraz.at/Members/Saffari/ssl-cvpr2010
![Page 2: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/2.jpg)
ICG
Professor Horst Cerjak, 19.12.20052
Horst Bischof SSL CVPR Tutorial
Typical Vision Tasks/Trends
Internet: Image Search/Classification Categorization
Huge Amounts of data, Huge labeling effort
![Page 3: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/3.jpg)
ICG
Professor Horst Cerjak, 19.12.20053
Horst Bischof SSL CVPR Tutorial
Typical Vision Tasks/Trends
Internet: Various Video and Image Databases
Huge Amounts of data, Partially/weakly labeled data
![Page 4: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/4.jpg)
ICG
Professor Horst Cerjak, 19.12.20054
Horst Bischof SSL CVPR Tutorial
Object Categorization
Typical Vision Tasks/Trends
Huge Amounts of data, Huge labeling effort
![Page 5: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/5.jpg)
ICG
Professor Horst Cerjak, 19.12.20055
Horst Bischof SSL CVPR Tutorial
VisipediaPerona 2009
![Page 6: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/6.jpg)
ICG
Professor Horst Cerjak, 19.12.20056
Horst Bischof SSL CVPR Tutorial
Surveillance: On-line data/Detection-Tracking
Typical Vision Tasks/Trends
Huge Amounts of data, On-line processing, Scene adaptation
![Page 7: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/7.jpg)
ICG
Professor Horst Cerjak, 19.12.20057
Horst Bischof SSL CVPR Tutorial
Many other tasks:• Tracking: On-line adaptation to object• Interactive segmentation: Changing model on
the fly• Interactive labeling: Suggestions as you label• …..
Typical Vision Tasks/Trends
![Page 8: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/8.jpg)
ICG
Professor Horst Cerjak, 19.12.20058
Horst Bischof SSL CVPR Tutorial
Requirements
Huge datasets
Unreliable (partial) labels
Changing environme
nts
![Page 9: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/9.jpg)
ICG
Professor Horst Cerjak, 19.12.20059
Horst Bischof SSL CVPR Tutorial
Requirements on Learner
On-line learning
RobustnessSemi-
supervised Learning
![Page 10: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/10.jpg)
ICG
Professor Horst Cerjak, 19.12.200510
Horst Bischof SSL CVPR Tutorial
Theory/Methods Covered
1. Semi-Supervised Learning2. Self-Training3. Generative Models4. Margin Assumption5. Cluster and Manifold Assumption6. Multi-View Learning7. Large-Scale, Multi-Class SSL and Online Learning8. Transfer Learning, Domain Adaptation, and Weakly
Related Data9. Multiple-Instance Learning
![Page 11: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/11.jpg)
ICG
Professor Horst Cerjak, 19.12.200511
Horst Bischof SSL CVPR Tutorial
Applications Covered
1. Object Detection2. Categorization3. Tracking4. Activity Recognition5. Segmentation
Using:BoostingRandom Forests
![Page 12: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/12.jpg)
ICG
Professor Horst Cerjak, 19.12.200512
Horst Bischof SSL CVPR Tutorial
Learning Tasks
• Unsupervised learning– Density estimation, Clustering, Dimensionality reduction.
• Semi-Supervised Clustering– Clustering with pair-wise constraints: must-link, cannot-link.
• Semi-Supervised Classification and Regression
• Supervised Learning– Classification, Regression.
![Page 13: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/13.jpg)
ICG
Professor Horst Cerjak, 19.12.200513
Horst Bischof SSL CVPR Tutorial
How do we get labels?Labels
![Page 14: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/14.jpg)
ICG
Professor Horst Cerjak, 19.12.200514
Horst Bischof SSL CVPR Tutorial
Semi-Supervised LearningSSL is Supervised Learning...
Goal: Estimate P(y|x) from Labeled DataDl={ (xi,yi) }
But: Additional Source tells about P(x)(e.g., Unlabeled Data Du={xj})
The Interesting Case:
)()()|()|(
xPypyxpxyp =
![Page 15: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/15.jpg)
ICG
Professor Horst Cerjak, 19.12.200515
Horst Bischof SSL CVPR Tutorial
Supervised learning
+ -
+ -
Maximum margin
![Page 16: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/16.jpg)
ICG
Professor Horst Cerjak, 19.12.200516
Horst Bischof SSL CVPR Tutorial
Can Unlabeled Data Help?
-?
-
???
?
?
?
?
?
?
????
?
??
??
?
? +?
+
???
?
?
?
????
?
?
?
?
?
?
?
?
? ?
low densityaround
decisionboundary
![Page 17: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/17.jpg)
ICG
Professor Horst Cerjak, 19.12.200517
Horst Bischof SSL CVPR Tutorial
SSL is biologically plausible
• Co-training by infants [Bahrick et.al. 2002]• Human change model once they see unlabeled data
[Zahki et.al. 2007,Zhu et.al. 2007,Vandist et.al. 2007]• Humans do On-line SSL [Zhu ICML 2010]
![Page 18: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/18.jpg)
ICG
Professor Horst Cerjak, 19.12.200518
Horst Bischof SSL CVPR Tutorial
Why?
1. Unlabelled data is cheap/free
2. Labeled data is hard to get
• human annotation is boring• labels may require experts• labels may require special devices• your graduate student is on vacation
![Page 19: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/19.jpg)
ICG
Professor Horst Cerjak, 19.12.200521
Horst Bischof SSL CVPR Tutorial
Online Learning in Perspective
Memory
Com
puta
tion
0 ∞0
∞
Online
Batch/Off-line
Incremental
![Page 20: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/20.jpg)
ICG
Professor Horst Cerjak, 19.12.200522
Horst Bischof SSL CVPR Tutorial
Why on-line learning?
Too much training data to fit in memory– Internet!!!
Sample generation process– Tracking, Co-Training
Changing processes– Changing Environment
![Page 21: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/21.jpg)
ICG
Professor Horst Cerjak, 19.12.200523
Horst Bischof SSL CVPR Tutorial
Why on-line learning?
Specializing– Forget irrelevant information– Specialize to current scene
Interactive Applications– Data labeling– Classifier Training– Specializing (Human in the loop)– Interactive Training (Segmentation)
![Page 22: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/22.jpg)
ICG
Professor Horst Cerjak, 19.12.200524
Horst Bischof SSL CVPR Tutorial
Robustness in Learning
Noisy input data
Label noise• Semi-supervised learning• Weakly-labeled data• Co-training• Self-learning• On-line learning
![Page 23: CVPR2010: Semi-supervised Learning in Vision: Part 1: Introduction](https://reader034.vdocument.in/reader034/viewer/2022042713/548d0e28b47959d30c8b64fd/html5/thumbnails/23.jpg)
ICG
Professor Horst Cerjak, 19.12.200525
Horst Bischof SSL CVPR Tutorial
Amir SaffariTheory
Christian LeistnerAlgorithms/Applications