Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and Classification

Loading...

Flash Player 9 (or above) is needed to view presentations.
We have detected that you do not have it on your computer. To install it, go here.

0 comments

Post a comment

    Post a comment
    Embed Video
    Edit your comment Cancel

    Favorites, Groups & Events

    Spatially Coherent Latent Topic Model For Concurrent Object Segmentation and Classification - Presentation Transcript

    1. Spatially coherent latent topic model for concurrent object segmentation and classification
      Authors: Liangliang Cao, Li Fei-Fei
      Presenter: Shao-Chuan Wang
    2. Outline
      Motivation
      A Review on Graphical Models
      Today’s topic: the paper
      Their 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. Outline
      Motivation
      A Review on Graphical Models
      Today’s topic: the paper
      Their Results
    5. Generative vs Discriminative
      Generative model: model p(x, y) or p(x|y)p(y)
      Discriminative model: model p(y|x)
      0.1
      0.05
      0
      0
      10
      20
      30
      40
      50
      60
      70
      1
      0.5
      0
      0
      10
      20
      30
      40
      50
      60
      70
      x = data
      From Prof. Antonio Torralba course slide
    6. Naïve Bayesian model
      (c: class, w: visual words)
      Once we have learnt the distribution, for a query image
      Generative model: An example
      Bayesian
      Networks
      c
      w1
      wn

    7. Generative model: Another example
      Mixture Gaussian Model
      How to infer from unlabeled data even if we
      know the underlining probability distribution structure?
      ?
    8. A graphical model
      Object class
      c
      P(c)
      Inverse Variance
      Mean
      γ
      μ
      P(γ|c)
      P(μ|c)
      Observed data
      x
      P(x|μ,γ)
      • Directed graph
      • Nodes represent variables
      Hidden
      • Links show dependencies
      • Conditional distributions at each node
    9. Inference of latent variables
      Expectation 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)
      • Use Gibbs sampling from the Posterior
      • Slow to converge
      • Variational method/Variational Message Passing (VMP)
      • Algorithms that convert inference problems into optimization problems (Opper and Saad 2001; Wainwright and Jordan 2003)
      Image from Wikipedia
    10. Outline
      Motivation
      A Review on Graphical Models
      Today’s topic: the paper
      Their Results
    11. Back to the topic: the paper
      bag of words
      Key Ideas:
      Latent topics are spatially coherent
      Generate topic distribution at the region level
      Over-segmentation, then merge by same topics
      Avoid obtaining regions larger than the objects
      One topic per region
      Can recognize objects with occlusion
      oversegmentation
      • Describe a region:
      • Homogeneous Appearance ar: average of color or texture features
      • SIFT-based visual words: wr
      • Concurrent segmentation and classification
    12. Spatial Latent Topic Model
      Notation:
      Image Id
      Region 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 θd
      P(θd|λ):
      Dirichlet prior of θd, parameterized by λ
      α, β:
      parameters describing the probability of generating appearance and visual words given topic
    13. Spatial Latent Topic Model (Unsupervised)
      Multinomial
      Dirichlet
      prior
      Maximize Log-likelihood
      an optimization problem: close-formed solution is intractable
    14. Variaitional Message Passing (Winn 2005)
      Coupling hidden variables θ, α, β makes the maximization intractable
      Instead, 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)
    15. 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,
    16. Variaitional Message Passing (Winn 2005)
      Eqn. (6) in the paper
      Bayesian networks
      representation
      Markov blanket:
    17. Spatial Latent Topic Model (Supervised)
      Now it becomes C x K matrix, i.e. θ depends on observed c
      For a query image,Id , find its most probable category c:
    18. Process
      Training step
      maximize total likelihood of training images, subject λ, α, θ and zr
      The learned λ, α are fixed
      Testing phase, for a query Image Id
      Estimate its θd and zr
      For classification task, find its most probable latent topics as its category
      For segmentation task, for the same zr, merge it.
      (3)
    19. Outline
      Motivation
      A Review on Graphical Models
      Today’s topic: the paper
      Their Results
    20. Experimental Results
      Unsupervised segmentation
      Occlusion case:
    21. Experimental Results
      Supervised segmentation
      Dataset
      13 classes of nature scenes
      # of training images: 100
      # of topics: 60
      # of categories: 13
    22. Experimental Results
      Supervised classification
      Dataset
      28 classes from Caltech 101
      # of training images: 30
      # of test images: 30
      # of topics in category: 28
      # of topics in clutter: 34
      6 background classes are
      left unlabeled
    23. ~ Thank you ~
    24. Variaitional Message Passing
      Following this framework, and use the graphical model provided by this paper:
    SlideShare Zeitgeist 2009

    + Shao-Chuan WangShao-Chuan Wang Nominate

    custom

    72 views, 0 favs, 1 embeds more stats

    A paper review

    More info about this document

    © All Rights Reserved

    Go to text version

    • Total Views 72
      • 66 on SlideShare
      • 6 from embeds
    • Comments 0
    • Favorites 0
    • Downloads 1
    Most viewed embeds
    • 6 views on http://shao-chuan.appspot.com

    more

    All embeds
    • 6 views on http://shao-chuan.appspot.com

    less

    Flagged as inappropriate Flag as inappropriate
    Flag as inappropriate

    Select your reason for flagging this presentation as inappropriate. If needed, use the feedback form to let us know more details.

    Cancel
    File a copyright complaint
    Having problems? Go to our helpdesk?

    Categories