Segmentation Through Optimization Pyry Matikainen He who fights
- Slides: 49
Segmentation Through Optimization Pyry Matikainen
“He who fights with monsters should look to it that he himself does not become a monster. ” -Friedrich Nietzsche, Beyond Good and Evil
Formulate Problem ly s e tiv sion c a i ro dec t Re ify st ju Force problem into favorite algorithm “Refine” Publish Gradient ascent via parameter tweaking
What is wrong with this? Formulate Problem ely ns v i t o ac cisi o tr de Re ify st ju Force problem into favorite algorithm “Refine” Publish • Difficult to use • Difficult to extend • Difficult to study Gradient ascent via parameter tweaking
Z. Tu and S. C. Zhu (2002) to the rescue! and also Ren and Malik (2003)…
Z. Tu and S. C. Zhu. Image Segmentation by Data-Driven Markov Chain Monte Carlo. PAMI, vol. 24, no. 5, pp. 657 -673, May, 2002: The DDMCMC paradigm combines and generalizes these [all other] segmentation methods in a principled way.
Segmenter Evaluator Optimizer
Everything is search.
Evaluator Optimizer
“What is a good segment? ” Ren and Malik (2003)
How do we model a segment? Texture Contours Raw pixel values
x 2 G(x) h(f(x)) G(b(x) - x)
(gaussian) (histogram) (gabor) (Bezier)
Number of regions Region perimeter length (smoothness) Notably absent: the data Region area Region appearance model complexity
Superpixels (normalized cuts) Oriented energy Brightness Texture (textons)
* Classifier G(W|I)
Evaluator Optimizer
MCMC is a technique for sampling from distributions.
Number of regions Region? ?
Ren and Malik Merge Split Boundary competition The ‘data driven’ part revealed! Model adaptation Switching image models
Data driven = do some clustering to make the MCMC faster.
Evaluator Optimizer
Tu & Zhu
Ren & Malik
Tu & Zhu New paradigm? Combines and generalizes other techniques? Principled? Good results? Ren & Malik 1/2 0 0 1 1/3
Evaluator Optimizer Evaluator
(gaussian) (mixture of gaussians) (3 x Bezier spline)
(g 1) (gaussian) (g 2) (histogram) (g 3) (gabor filter) (g 4) (Bezier spline)
Number of regions Region appearance model parameters Region appearance model Pixels in region
MCMC
Xiaofeng Ren and Jitendra Malik. Learning a Classification Model for Segmentation. ICCV 2003.
Boundary between i and j
Classification certainty Tu and Zhu 2002 Sampling P(W|I) Generative models Pixels Ren and Malik 2003 Maximizing G(W|I) Discriminative models Superpixels
- Pyry lehtonen
- Pyry lehtonen
- Juha matikainen
- Sini matikainen
- Sanna matikainen
- The americans chapter 19
- Anger is at the root of most arguments and many fights.
- Ikea cancer
- Guided reading wilson fights for peace
- The new deal fights the depression
- How can anger and revenge lead to fights
- Which macromolecule stores energy
- Fiona fights robin hood
- What causes fights and quarrels
- Chapter 19 section 4 wilson fights for peace
- A new deal fights the depression
- Targeting strategy
- Furcation involvement
- Disadvantages of timber conversion
- Nissim ezekiel night of the scorpion
- By one man sin
- Quadratic word problems
- Aircraft maintenance schedule optimization
- Ram optimization pack
- Group policy change management
- Jquery optimization selectors
- Joptimizer
- Max simkoff
- Cognos 8 performance tuning
- Return pass jnl
- Onap optimization framework
- Fun optimization problems
- 010001011
- Googlle slides
- Workforce optimization avaya
- Humidity 2 optimization
- Global optimization toolbox
- Convex optimization in machine learning javatpoint
- Metode fibonacci
- Cosmos db query optimization
- Ganetxl
- Optimization techniques
- Machine dependent code
- Voyager plant optimization
- Matriks hessian 3 variabel
- Espresso automation
- Optimization ap calculus
- Sam optimization model
- Lagrange multiplier
- Sam optimization model