WordPress Websites for Engineers: Elevate Your Brand
Fcv learn learned-miller
1. Learning on the Fly:
Rapid Adaptation to the Image
Erik Learned-Miller
with Vidit Jain, Gary Huang,
Laura Sevilla Lara, Manju Narayana,
Ben Mears
Computer Science Department
2. “Traditional” machine learning
Learning happens from large data sets
• With labels: supervised learning
• Without labels: unsupervised learning
• Mixed labels: semi-supervised learning,
transfer learning,
learning from one (labeled) example,
self-taught learning,
domain adaptation
Learning on the Fly 2
3. Learning on the Fly
Given:
• A learning machine trained with traditional methods
• a single test image (no labels)
Learn from the test image!
Learning on the Fly 3
4. Learning on the Fly
Given:
• A learning machine trained with traditional methods
• a single test image (no labels)
Learn from the test image!
• Domain adaptation where the “domain” is the new
image
• No covariate shift assumption.
• No new labels
Learning on the Fly 4
5. An Example in Computer Vision
Parsing Images of Architectural Scenes
Berg, Grabler, and Malik ICCV 2007.
• Detect easy or “canonical” stuff.
• Use easily detected stuff to bootstrap models of harder
stuff.
Learning on the Fly 5
6. Claim
This is so easy and routine for humans that it’s
hard to realize we’re doing it.
• Another example…
Learning on the Fly 6
10. What about traditional methods…
Hidden Markov Model for text recognition:
• Appearance model for characters
• Language model for labels
• Use Viterbi to do joint inference
Learning on the Fly 10
11. What about traditional methods…
Hidden Markov Model for text recognition:
• Appearance model for characters
• Language model for labels
• Use Viterbi to do joint inference
DOESN’T WORK!
Prob( |Label=A) cannot be well estimated,
fouling up the whole process.
Learning on the Fly 11
12. Lessons
We must assess when our models are broken,
and use other methods to proceed….
• Current methods of inference assume probabilities are
correct!
• “In vision, probabilities are often junk.”
• Related to similarity becoming meaningless beyond a
certain distance.
Learning on the Fly 12
13. 2 Examples
Face detection (CVPR 2011)
OCR (CVPR 2010)
Learning on the Fly 13
14. Preview of results: Finding false negatives
Viola-Jones Learning on the Fly
Learning on the Fly 14
18. Run a pre-existing detector...
Key
Face
Non-face
Close to
boundary
Learning on the Fly 18
19. Gaussian Process Regression
learn smooth mapping
from appearance to score
negative positive
apply mapping to borderline
patches
Learning on the Fly 19
21. Comments
No need to retrain original detector
• It wouldn’t change anyway!
No need to access original training data
Still runs in real-time
GP regression is done for every new image.
Learning on the Fly 21
22. Noisy Document
Initial Transcription
We fine herefore t
linearly rolatcd to the
when this is calculated
equilibriurn. In short,
on the null-hypothesis:
Learning on the Fly 22
23. Premise
We would like to fine confident words
to build a document-specific model,
but it is difficult to estimate Prob(error).
However, we can bound Prob(error).
Now, select words with
• Prob(error)<epsilon.
Learning on the Fly 23
25. Document specific OCR
Extract clean sets (error bounded sets)
Build document-specific models from clean set
characters
Reclassify other characters in document
• 30% error reduction on 56 documents.
Learning on the Fly 25
26. Summary
Many applications of learning on the fly.
Adaptation and bootstrapping new models is
more common in human learning than is
generally believed.
Starting to answer the question: “How can we do
domain adaptation from a single image?”
Learning on the Fly 26
