Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and Classification
Download as PPTX, PDF1 like2,234 views
The document summarizes a research paper on spatially coherent latent topic modeling for concurrent object segmentation and classification from images. The proposed model represents images as a collection of regions, each associated with a latent topic. It incorporates spatial relationships between regions by encouraging neighboring regions to take on similar topics. The model is trained using variational message passing to maximize the log likelihood of image data. Experimental results show the model can segment objects even under occlusion and achieve good performance on supervised classification tasks using natural scene images.
Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and Classification
- 1. Spatially coherent latent topic model for concurrent object segmentation and classificationAuthors: Liangliang Cao, Li Fei-FeiPresenter: Shao-Chuan Wang
- 2. OutlineMotivationA Review on Graphical ModelsToday’s topic: the paperTheir Results
- 3. Motivation: Real world problem often full of “noises”Bags of words (local features)Spatial relationships of objects are ignored (has its limit)When classify a test image, what is its “subject” ?Flag?Banner?People?Sports field?From Prof. Fei-Fei’s ICCV09 tutorial slide
- 4. OutlineMotivationA Review on Graphical ModelsToday’s topic: the paperTheir Results
- 5. Generative vs Discriminative Generative model: model p(x, y) or p(x|y)p(y)Discriminative model: model p(y|x)0.10.05001020304050607010.50010203040506070x = dataFrom Prof. Antonio Torralba course slide
- 6. Naïve Bayesian model (c: class, w: visual words)Once we have learnt the distribution, for a query imageGenerative model: An exampleBayesianNetworkscw1wn…
- 7. Generative model: Another exampleMixture Gaussian ModelHow to infer from unlabeled data even if weknow the underlining probability distribution structure? ?
- 8. A graphical modelObject classcP(c)Inverse VarianceMeanγμP(γ|c)P(μ|c)Observed dataxP(x|μ,γ)Directed graph
- 9. Nodes represent variablesHiddenLinks show dependencies
- 10. Conditional distributions at each nodeInference of latent variablesExpectation maximization (EM)“Soft guess” latent variable first (E-step)Based on latent variable (assume it is correct), solve optimization problem (M-step)Markov-chain Monte Carlo (MCMC)
- 11. Use Gibbs sampling from the Posterior
- 12. Slow to converge
- 13. Variational method/Variational Message Passing (VMP)
- 14. Algorithms that convert inference problems into optimization problems (Opper and Saad 2001; Wainwright and Jordan 2003)Image from Wikipedia
- 15. OutlineMotivationA Review on Graphical ModelsToday’s topic: the paperTheir Results
- 16. Back to the topic: the paperbag of wordsKey Ideas:Latent topics are spatially coherentGenerate topic distribution at the region levelOver-segmentation, then merge by same topicsAvoid obtaining regions larger than the objectsOne topic per regionCan recognize objects with occlusionoversegmentationDescribe a region:
- 17. Homogeneous Appearance ar: average of color or texture features
- 18. SIFT-based visual words: wr
- 19. Concurrent segmentation and classificationSpatial Latent Topic ModelNotation:Image IdRegion r = {1,2,…,Rd}Latent topic zr= {1,2,…,K}appearance ar = {1,2,…,A}visual words wr = (wr1,wr2,…, wrMr); wr1 = {1,2,…,W}P(zr |θd): topic probability (Multinomial distribution) parameterized by θdP(θd|λ): Dirichlet prior of θd, parameterized by λα, β: parameters describing the probability of generating appearance and visual words given topic
- 20. Spatial Latent Topic Model (Unsupervised)MultinomialDirichletpriorMaximize Log-likelihoodan optimization problem: close-formed solution is intractable
- 21. Variaitional Message Passing (Winn 2005)Coupling hidden variables θ, α, β makes the maximization intractableInstead, maximize the lower bound of L Goal: Find a tractable Q(H) that closely approximates the true posterior distribution P(H|V) (equality holds for any distribution Q)←Or equivalently, minimize KL(Q||P)
- 22. Variaitional Message Passing (Winn 2005)Further factorization assumptions (Jordan et al., 1999; Jaakkola, 2001; Parisi, 1988) (restrict the family of distributions Q)Entropy term=Where,
- 23. Variaitional Message Passing (Winn 2005)Eqn. (6) in the paperBayesian networks representationMarkov blanket:
- 24. Spatial Latent Topic Model (Supervised)Now it becomes C x K matrix, i.e. θ depends on observed cFor a query image,Id , find its most probable category c:
- 25. ProcessTraining stepmaximize total likelihood of training images, subject λ, α, θ and zrThe learned λ, α are fixedTesting phase, for a query Image IdEstimate its θd and zrFor classification task, find its most probable latent topics as its categoryFor segmentation task, for the same zr, merge it.(3)
- 26. OutlineMotivationA Review on Graphical ModelsToday’s topic: the paperTheir Results
- 28. Experimental ResultsSupervised segmentationDataset13 classes of nature scenes# of training images: 100# of topics: 60# of categories: 13
- 29. Experimental ResultsSupervised classificationDataset28 classes from Caltech 101# of training images: 30# of test images: 30# of topics in category: 28# of topics in clutter: 346 background classes are left unlabeled
- 30. ~ Thank you ~
- 31. Variaitional Message PassingFollowing this framework, and use the graphical model provided by this paper: