SlideShare ist ein Scribd-Unternehmen logo
1 von 28
Downloaden Sie, um offline zu lesen
Patch matching with polynomial
exponential families and
projective divergences
Frank Nielsen 1 Richard Nock2
1École Polytechnique & Sony CSL
2Data61 & Australian National University
9th Similarity Search and Applications
1/27
The “Patch Matching” problem
Given a query patch, patch matching = finding “similar” patches
in a target image.
Handle noise, symmetry [16, 19], zoom, smooth deformation, etc.
2/27
Patch Matching: Baseline (naïve) algorithm
Sum of Square Differences (SSDs) of the pixel intensities:
D(Is, It(x0)) =
x∈[1,ws ]×[1,hs ]
(Is(x) − It(x + x0))2
(= squared Euclidean distance on vectorized patch intensities)
but small image shift can cause large 2
2 distance
shift [18]
Naïve brute-force algorithm in O(wthtwshs) too time
consuming!
→ extend to multiple color channels with sum/max
Alternative method: Fourier phase correlation method [11, 8]
in O(wh log(wh)) but limited to translations
Factorize computations using Nearest Neighbor Fields [3, 4]
(+ GPU)
3/27
Large patch PM application: Zoom stitching
Nested image mosaicing: one image is a patch fully contained
inside another image
4/27
Experiments: brute-force baseline algorithm
Image of size 1280, patch of size 120 × 120
SSD 30.7 sec
SSDRGBSum 96.7 sec
SSDRGBMax 208.7 sec
HP Elitebook 840 G1 (i7-4600U CPU 2.1 GHz with 8 GB RAM)
5/27
Experiments for the baseline algorithm
HP Elitebook 840 G1 (i7-4600U CPU 2.1 GHz with 8 GB RAM)
Complexity O(wthtwshs) does not scale!
image size
500 × 300 960 × 640 1500 × 1000
patch
size
50 × 50 0.82 3.70 8.83
100 × 100 1.31 8.81 20.34
200 × 200 0.79 15.34 66.70
SSDRGBSum (in sec):
image size
500 × 300 960 × 640 1500 × 1000
patch
size
50 × 50 2.20 11.63 19.95
100 × 100 3.88 23.68 63.71
200 × 200 2.22 43.14 161.51
6/27
Our proposed method:
PEF-PM
Polynomial Exponential
Family-Patch Matching
7/27
PEF-PM: Polynomial Exponential Family-PM
Polynomial exponential family:
p(x; θ) = exp( D
i=1 θi xi − F(θ))
t(x) = (x1, . . . , xD) = sufficient statistics [5, 1], θ = natural
parameters. x, y = x y ∈ R = Euclidean inner product.
F(θ) = log exp( θ, t(x) )dx = log-normalizer
→ However F = log exp( θ, t(x) )dx not available in
closed-form!
Estimate θ using Score Matching Estimator [10]
(SME, instead of Maximum Likelihood Estimator, MLE)
Define projective distance D between PEFs to cope with
unnormalized distributions:
D(λq, λ q ) = D(q, q ) for any λ, λ > 0
Accelerate batched SMEs using integral images
= Summed Area Tables (SATs)
8/27
Score Matching Estimator [10] (SME) for PEFs
Divergence estimator: minimize the Fisher divergence:
J(p : q) =
1
2
d
i=1
∂ log p(x)
∂xi
−
∂ log q(x)
∂xi
2
p(x)dx,
with J(p : q) = 0 iff p = λq for λ > 0. Fisher divergence is
one-sided projective divergence: J(p : λq) = J(p : q).
For univariate Polynomial Exponential Families, SME:
θSM(s(x)) = − (Es[A(x)])−1
(Es[b(x)])
where A(x) = [ti (x)tj (x)] (D × D symmetric matrix) and
b(x) = [t1 (x) . . . tD(x)] (D-dimensional column vector). For
PEFs, ti (x) = ixi−1 and ti (x) = i(i − 1)xi−2, and therefore
A = Es[A(x)] = [aij = ijMi+j−2(s)] and
b = Es[b(x)] = [bj = j(j − 1)Mj−2(s)], where
Ml (s) = 1
s i xl
i is the l-th sample raw moment.
9/27
Accelerating batched SMEs for PEFs using SATs
To perform Score Matching in OD(1), use SATs:
Summed Area Tables [7] (SATs), also called integral
images:
∀(x, y), F(x, y) =
x ≤x,y ≤y
f (x , y )
Single pass computation in preprocessing
Then patch PEF SME (f = t , t , a rectangle bottom-left
corner n(x0, y0) and top-right corner (x1, y1)) in O(1) time:
x0≤x≤x1,y0≤y≤y1
f (x, y) = F(x1, y1)+F(x0, y0)−F(x0, y1)−F(x1, y0)
10/27
Similarity between PEFs: Projective divergences
Relative entropy called the Kullback-Leibler divergence:
KL(p(x; θs), p(x; θt)) =
x∈R+
p(x; θs) log
p(x; θs)
p(x; θt)
dx
amounts to Bregman divergence for exponential families [2], but
need F in closed-form.
Projective γ-divergence [9, 15, 6] (for γ > 0):
Dγ(λq, λ q ) = Dγ(q, q ) for any λ, λ > 0
Dγ(p, q) =
1
γ(γ − 1)
log
pγ(x)q1−γ(x)dx)
( p(x)dx)γ( q(x)dx)1−γ
Dγ(p, q) =
1
γ(1 + γ)
log Iγ(p, p) −
1
γ
log Iγ(p, q) +
1
1 + γ
log Iγ(q, q)
where
Iγ(p, q) =
x∈X
p(x)q(x)γ
dx.
11/27
Projective γ-divergences for exponential families
Use the symmetrized γ-divergence Sγ for patch similarity.
When γ → 0, Dγ(p, q) → KL(p, q) (Bregman divergence for
EFs)
Iγ(θp, θq) = exp (F(θp + γθq) − F(θp) − γF(θq)) .
Provided that the γθp + θq ∈ Θ. Condition always satisfied
when the natural parameter space [12, 14, 13] is a cone (since
γ > 0), like the multivariate Gaussians distributions, the
multinomial distributions, and the Wishart distributions, just
to name a few.
12/27
Monte-Carlo stochastic estimation of Sγ
Although projective divergence, exact Dγ depends on the
untractable log-normalizer!
Approximate Iγ(p, q) by discretizing the integral using
quadrature rules
Monte-Carlo stochastic integration (γ = 0.1, s = 100000):
Iγ(p, q) =
x∈X
p(x)q(x)γ
dx
1
m
m
i=1
q(xi )γ
with x1, ..., xs ∼ p(x) (iid)
→ Sample variance, confidence interval (CI) of Monte-Carlo
estimator.
13/27
Results of PEF-PM
Impact of the polynomial degree of PEFs, the order D of the
exponential family
order D = 3 order D = 4
order D = 5 order D = 6
Image size 1280 × 853, patch size 100 × 100
14/27
Profiling PEF-PM timings
Computational time in seconds for PEFs.
degree of PEF
2 3 4 5 6
SAT construction 5.99 6.37 8.04 9.56 11.86
PEF estimation (SM) 5.24 7.44 8.96 12.84 14.82
Sγ search 7.02 8.86 9.70 10.30 10.52
Baseline:
image size
500 × 300 960 × 640 1500 × 1000
patch
size
50 × 50 0.82 3.70 8.83
100 × 100 1.31 8.81 20.34
200 × 200 0.79 15.34 66.70
15/27
PEFs handles patch symmetries (→ bag of pixels)
Patch matching with symmetry (reflection) detected by PEF-PM of
order 6
patch size 250 × 250, image dimension (960, 640)
16/27
Summary of contributions
Model patch colors using Polynomial Exponential Families
(PEFs), universal smooth (positive) densities
Estimate PEFs using Score Matching Estimator, and
accelerate the batch estimator using Summed Area Tables
(SATs)
Use a statistical projective divergence: the symmetrized
γ-divergence.
Closed-form expression for EFs with log-normalizer F
Monte-Carlo estimation without explicit log-normalizer
Handle noise robustly (γ-divergence), symmetries (color
distributions), etc. (see paper)
17/27
From a historical view of statistical distances...
18/27
... To a structural view of classes of distances
If (P : Q) = p(x)f (q(x)
p(x) dν(x)
BF (P : Q) = F(P) − F(Q) − P − Q, F(Q)
tBF (P : Q) = BF (P :Q)
√
1+ F (Q) 2
CD,g(P : Q) = g(Q)D(P : Q)
BF,g(P : Q; W) = WBF
P
Q : Q
W
Dv
(P : Q) = D(v(P) : v(Q))
v-Divergence Dv
total Bregman divergence tB(· : ·) Bregman divergence BF (· : ·)
conformal divergence CD,g(· : ·)
Csisz´ar f-divergence If (· : ·)
scaled Bregman divergence BF (· : ·; ·)
scaled conformal divergence CD,g(· : ·; ·)
Dissimilarity measure
Divergence
Projective divergence
γ-divergence
H¨yvarinen SM/RM
D(λp : λ p ) = D(p : p )
D(λp : p ) = D(p : p )
one-sided
double sided
C3
Axiomatic approach, exhausitivity characteristics
19/27
Edited books:
2012 2014 2016
3rd edition GSI’17: www.gsi2017.org
Geometric Sciences of Information, Paris, Fall 2017
20/27
Thank you
Acknowledgments:
We gratefully thank Quei-An Chen (École Polytechnique, France)
for implementing our patch matching system and performing
various experiments.
21/27
References I
S.-i. Amari.
Information Geometry and Its Applications.
Applied Mathematical Sciences. Springer Japan, 2016.
Arindam Banerjee, Srujana Merugu, Inderjit S Dhillon, and Joydeep Ghosh.
Clustering with Bregman divergences.
The Journal of Machine Learning Research, 6:1705–1749, 2005.
Connelly Barnes, Eli Shechtman, Adam Finkelstein, and Dan B Goldman.
Patchmatch: a randomized correspondence algorithm for structural image editing.
ACM Transactions on Graphics (TOG), 28(3):24, 2009.
Connelly Barnes, Eli Shechtman, Dan B Goldman, and Adam Finkelstein.
The generalized patchmatch correspondence algorithm.
In European Conference on Computer Vision (ECCV), pages 29–43. Springer, 2010.
Lawrence D Brown.
Fundamentals of statistical exponential families with applications in statistical decision theory.
Lecture Notes-monograph series, 9:i–279, 1986.
Ting-Li Chen, Dai-Ni Hsieh, Hung Hung, I-Ping Tu, Pei-Shien Wu, Yi-Ming Wu, Wei-Hau Chang,
Su-Yun Huang, et al.
γ-sup: A clustering algorithm for cryo-electron microscopy images of asymmetric particles.
The Annals of Applied Statistics, 8(1):259–285, 2014.
Franklin C Crow.
Summed-area tables for texture mapping.
ACM SIGGRAPH computer graphics, 18(3):207–212, 1984.
22/27
References II
Hassan Foroosh, Josiane B Zerubia, and Marc Berthod.
Extension of phase correlation to subpixel registration.
IEEE Transactions onImage Processing, 11(3):188–200, 2002.
Hironori Fujisawa and Shinto Eguchi.
Robust parameter estimation with a small bias against heavy contamination.
Journal of Multivariate Analysis, 99(9):2053–2081, 2008.
Aapo Hyvärinen.
Estimation of non-normalized statistical models by score matching.
Journal of Machine Learning Research, 6(Apr):695–709, 2005.
CD Kuglin.
The phase correlation image alignment method.
In Proc. Int. Conf. on Cybernetics and Society, 1975, pages 163–165, 1975.
Frank Nielsen.
Closed-form information-theoretic divergences for statistical mixtures.
In Pattern Recognition (ICPR), 21st International Conference on, pages 1723–1726. IEEE, 2012.
Frank Nielsen and Richard Nock.
A closed-form expression for the Sharma-Mittal entropy of exponential families.
Journal of Physics A: Mathematical and Theoretical, 45(3):032003, 2011.
Frank Nielsen and Richard Nock.
On the chi square and higher-order chi distances for approximating f -divergences.
IEEE Signal Processing Letters, 1(21):10–13, 2014.
Akifumi Notsu, Osamu Komori, and Shinto Eguchi.
Spontaneous clustering via minimum gamma-divergence.
Neural computation, 26(2):421–448, 2014.
23/27
References III
Viorica Patraucean, Rafael Gioi, and Maks Ovsjanikov.
Detection of mirror-symmetric image patches.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops,
pages 211–216, 2013.
Carsten Rother, Vladimir Kolmogorov, and Andrew Blake.
Grabcut: Interactive foreground extraction using iterated graph cuts.
ACM transactions on graphics (TOG), 23(3):309–314, 2004.
Lucas Theis, Aäron van den Oord, and Matthias Bethge.
A note on the evaluation of generative models.
arXiv preprint arXiv:1511.01844, 2015.
ICLR 2016.
Z. Wang, Z. Tang, and X. Zhang.
Reflection symmetry detection using locally affine invariant edge correspondence.
IEEE Transactions on Image Processing, 24(4):1297–1301, April 2015.
24/27
Perspectives and future work
Model selection of the polynomial exponential family according
to the query patch
Foreground/background detection in patches (say, using
Grabcut [17]) and matching only the foreground statistical
distributions to improve the accuracy of patch matching.
Modeling by distributions allows us to discard rectangular
windows.
Multivariate PEFs to bypass sum/max of univariate PEF color
channel distances
Handle clamped support [0, 255] instead of [0, +∞)
25/27
Qualitative results of PEF-PM
patch size 150 × 150 and image size 960 × 640
aligned pixel-based (SSD) PEF (D = 4) with Sγ
Intensity
Sum SSD
26/27
Acceptance-rejection sampling
accept
reject
y
u ∝ f(x)
Mg(x)
u < f(y)
Mg(y)
27/27
Acceptance-rejection sampling for PEFs
f (x) ∝ ePθ(x) with polynomial P(x) = D
i=1 θi xi ,
θ = (θ1, ..., θD) defined on support X = [0, 255].
Computationally intractable normalizer Z(θ) = x∈X ePθ(x)dx.
Proposal distribution g(y) = 1
255 , uniform density on X
f (x) ≤ Mθg(x) for Mθ = 255 exp(maxx∈X Pθ(x)).
maxx∈X Pθ(x) ≤ D
i=1 maxx∈X θi xi = D
i=1(θi 255i )+. In
particular, Mθ = 255 when ∀i, θi ≤ 0.
Draw variate u ∼ Unif(0, 1) and variate y ∼ Unif(0, 255). If
u < f (y)
Mθg(y) accept y as variate of f (x), otherwise reject it.
Expected M iterations for drawing a variate of f (x)

Weitere ähnliche Inhalte

Was ist angesagt?

On the Jensen-Shannon symmetrization of distances relying on abstract means
On the Jensen-Shannon symmetrization of distances relying on abstract meansOn the Jensen-Shannon symmetrization of distances relying on abstract means
On the Jensen-Shannon symmetrization of distances relying on abstract meansFrank Nielsen
 
Clustering in Hilbert simplex geometry
Clustering in Hilbert simplex geometryClustering in Hilbert simplex geometry
Clustering in Hilbert simplex geometryFrank Nielsen
 
On learning statistical mixtures maximizing the complete likelihood
On learning statistical mixtures maximizing the complete likelihoodOn learning statistical mixtures maximizing the complete likelihood
On learning statistical mixtures maximizing the complete likelihoodFrank Nielsen
 
Clustering in Hilbert geometry for machine learning
Clustering in Hilbert geometry for machine learningClustering in Hilbert geometry for machine learning
Clustering in Hilbert geometry for machine learningFrank Nielsen
 
ABC based on Wasserstein distances
ABC based on Wasserstein distancesABC based on Wasserstein distances
ABC based on Wasserstein distancesChristian Robert
 
ABC with Wasserstein distances
ABC with Wasserstein distancesABC with Wasserstein distances
ABC with Wasserstein distancesChristian Robert
 
A nonlinear approximation of the Bayesian Update formula
A nonlinear approximation of the Bayesian Update formulaA nonlinear approximation of the Bayesian Update formula
A nonlinear approximation of the Bayesian Update formulaAlexander Litvinenko
 
Density theorems for Euclidean point configurations
Density theorems for Euclidean point configurationsDensity theorems for Euclidean point configurations
Density theorems for Euclidean point configurationsVjekoslavKovac1
 
NCE, GANs & VAEs (and maybe BAC)
NCE, GANs & VAEs (and maybe BAC)NCE, GANs & VAEs (and maybe BAC)
NCE, GANs & VAEs (and maybe BAC)Christian Robert
 

Was ist angesagt? (20)

On the Jensen-Shannon symmetrization of distances relying on abstract means
On the Jensen-Shannon symmetrization of distances relying on abstract meansOn the Jensen-Shannon symmetrization of distances relying on abstract means
On the Jensen-Shannon symmetrization of distances relying on abstract means
 
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
 
Clustering in Hilbert simplex geometry
Clustering in Hilbert simplex geometryClustering in Hilbert simplex geometry
Clustering in Hilbert simplex geometry
 
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Appli...
 Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Appli... Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Appli...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Appli...
 
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
 
On learning statistical mixtures maximizing the complete likelihood
On learning statistical mixtures maximizing the complete likelihoodOn learning statistical mixtures maximizing the complete likelihood
On learning statistical mixtures maximizing the complete likelihood
 
Clustering in Hilbert geometry for machine learning
Clustering in Hilbert geometry for machine learningClustering in Hilbert geometry for machine learning
Clustering in Hilbert geometry for machine learning
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
ABC based on Wasserstein distances
ABC based on Wasserstein distancesABC based on Wasserstein distances
ABC based on Wasserstein distances
 
ABC with Wasserstein distances
ABC with Wasserstein distancesABC with Wasserstein distances
ABC with Wasserstein distances
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
CLIM Fall 2017 Course: Statistics for Climate Research, Spatial Data: Models ...
CLIM Fall 2017 Course: Statistics for Climate Research, Spatial Data: Models ...CLIM Fall 2017 Course: Statistics for Climate Research, Spatial Data: Models ...
CLIM Fall 2017 Course: Statistics for Climate Research, Spatial Data: Models ...
 
CLIM Fall 2017 Course: Statistics for Climate Research, Statistics of Climate...
CLIM Fall 2017 Course: Statistics for Climate Research, Statistics of Climate...CLIM Fall 2017 Course: Statistics for Climate Research, Statistics of Climate...
CLIM Fall 2017 Course: Statistics for Climate Research, Statistics of Climate...
 
A nonlinear approximation of the Bayesian Update formula
A nonlinear approximation of the Bayesian Update formulaA nonlinear approximation of the Bayesian Update formula
A nonlinear approximation of the Bayesian Update formula
 
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
 
Density theorems for Euclidean point configurations
Density theorems for Euclidean point configurationsDensity theorems for Euclidean point configurations
Density theorems for Euclidean point configurations
 
NCE, GANs & VAEs (and maybe BAC)
NCE, GANs & VAEs (and maybe BAC)NCE, GANs & VAEs (and maybe BAC)
NCE, GANs & VAEs (and maybe BAC)
 

Andere mochten auch

Traitement des données massives (INF442, A1)
Traitement des données massives (INF442, A1)Traitement des données massives (INF442, A1)
Traitement des données massives (INF442, A1)Frank Nielsen
 
Traitement massif des données 2016
Traitement massif des données 2016Traitement massif des données 2016
Traitement massif des données 2016Frank Nielsen
 
(ISIA 5) Cours d'algorithmique (1995)
(ISIA 5) Cours d'algorithmique (1995)(ISIA 5) Cours d'algorithmique (1995)
(ISIA 5) Cours d'algorithmique (1995)Frank Nielsen
 
Traitement des données massives (INF442, A3)
Traitement des données massives (INF442, A3)Traitement des données massives (INF442, A3)
Traitement des données massives (INF442, A3)Frank Nielsen
 
Traitement des données massives (INF442, A7)
Traitement des données massives (INF442, A7)Traitement des données massives (INF442, A7)
Traitement des données massives (INF442, A7)Frank Nielsen
 
Traitement des données massives (INF442, A2)
Traitement des données massives (INF442, A2)Traitement des données massives (INF442, A2)
Traitement des données massives (INF442, A2)Frank Nielsen
 
Traitement des données massives (INF442, A5)
Traitement des données massives (INF442, A5)Traitement des données massives (INF442, A5)
Traitement des données massives (INF442, A5)Frank Nielsen
 
On representing spherical videos (Frank Nielsen, CVPR 2001)
On representing spherical videos (Frank Nielsen, CVPR 2001)On representing spherical videos (Frank Nielsen, CVPR 2001)
On representing spherical videos (Frank Nielsen, CVPR 2001)Frank Nielsen
 
Traitement des données massives (INF442, A6)
Traitement des données massives (INF442, A6)Traitement des données massives (INF442, A6)
Traitement des données massives (INF442, A6)Frank Nielsen
 
Computational Information Geometry for Machine Learning
Computational Information Geometry for Machine LearningComputational Information Geometry for Machine Learning
Computational Information Geometry for Machine LearningFrank Nielsen
 

Andere mochten auch (10)

Traitement des données massives (INF442, A1)
Traitement des données massives (INF442, A1)Traitement des données massives (INF442, A1)
Traitement des données massives (INF442, A1)
 
Traitement massif des données 2016
Traitement massif des données 2016Traitement massif des données 2016
Traitement massif des données 2016
 
(ISIA 5) Cours d'algorithmique (1995)
(ISIA 5) Cours d'algorithmique (1995)(ISIA 5) Cours d'algorithmique (1995)
(ISIA 5) Cours d'algorithmique (1995)
 
Traitement des données massives (INF442, A3)
Traitement des données massives (INF442, A3)Traitement des données massives (INF442, A3)
Traitement des données massives (INF442, A3)
 
Traitement des données massives (INF442, A7)
Traitement des données massives (INF442, A7)Traitement des données massives (INF442, A7)
Traitement des données massives (INF442, A7)
 
Traitement des données massives (INF442, A2)
Traitement des données massives (INF442, A2)Traitement des données massives (INF442, A2)
Traitement des données massives (INF442, A2)
 
Traitement des données massives (INF442, A5)
Traitement des données massives (INF442, A5)Traitement des données massives (INF442, A5)
Traitement des données massives (INF442, A5)
 
On representing spherical videos (Frank Nielsen, CVPR 2001)
On representing spherical videos (Frank Nielsen, CVPR 2001)On representing spherical videos (Frank Nielsen, CVPR 2001)
On representing spherical videos (Frank Nielsen, CVPR 2001)
 
Traitement des données massives (INF442, A6)
Traitement des données massives (INF442, A6)Traitement des données massives (INF442, A6)
Traitement des données massives (INF442, A6)
 
Computational Information Geometry for Machine Learning
Computational Information Geometry for Machine LearningComputational Information Geometry for Machine Learning
Computational Information Geometry for Machine Learning
 

Ähnlich wie Patch Matching with Polynomial Exponential Families and Projective Divergences

Slides: A glance at information-geometric signal processing
Slides: A glance at information-geometric signal processingSlides: A glance at information-geometric signal processing
Slides: A glance at information-geometric signal processingFrank Nielsen
 
k-MLE: A fast algorithm for learning statistical mixture models
k-MLE: A fast algorithm for learning statistical mixture modelsk-MLE: A fast algorithm for learning statistical mixture models
k-MLE: A fast algorithm for learning statistical mixture modelsFrank Nielsen
 
Murphy: Machine learning A probabilistic perspective: Ch.9
Murphy: Machine learning A probabilistic perspective: Ch.9Murphy: Machine learning A probabilistic perspective: Ch.9
Murphy: Machine learning A probabilistic perspective: Ch.9Daisuke Yoneoka
 
Slides: Hypothesis testing, information divergence and computational geometry
Slides: Hypothesis testing, information divergence and computational geometrySlides: Hypothesis testing, information divergence and computational geometry
Slides: Hypothesis testing, information divergence and computational geometryFrank Nielsen
 
Slides: The dual Voronoi diagrams with respect to representational Bregman di...
Slides: The dual Voronoi diagrams with respect to representational Bregman di...Slides: The dual Voronoi diagrams with respect to representational Bregman di...
Slides: The dual Voronoi diagrams with respect to representational Bregman di...Frank Nielsen
 
Low rank tensor approximation of probability density and characteristic funct...
Low rank tensor approximation of probability density and characteristic funct...Low rank tensor approximation of probability density and characteristic funct...
Low rank tensor approximation of probability density and characteristic funct...Alexander Litvinenko
 
Computational Information Geometry on Matrix Manifolds (ICTP 2013)
Computational Information Geometry on Matrix Manifolds (ICTP 2013)Computational Information Geometry on Matrix Manifolds (ICTP 2013)
Computational Information Geometry on Matrix Manifolds (ICTP 2013)Frank Nielsen
 
QMC Error SAMSI Tutorial Aug 2017
QMC Error SAMSI Tutorial Aug 2017QMC Error SAMSI Tutorial Aug 2017
QMC Error SAMSI Tutorial Aug 2017Fred J. Hickernell
 
Testing for mixtures by seeking components
Testing for mixtures by seeking componentsTesting for mixtures by seeking components
Testing for mixtures by seeking componentsChristian Robert
 
Pattern learning and recognition on statistical manifolds: An information-geo...
Pattern learning and recognition on statistical manifolds: An information-geo...Pattern learning and recognition on statistical manifolds: An information-geo...
Pattern learning and recognition on statistical manifolds: An information-geo...Frank Nielsen
 
Bayesian inference on mixtures
Bayesian inference on mixturesBayesian inference on mixtures
Bayesian inference on mixturesChristian Robert
 
Workshop in honour of Don Poskitt and Gael Martin
Workshop in honour of Don Poskitt and Gael MartinWorkshop in honour of Don Poskitt and Gael Martin
Workshop in honour of Don Poskitt and Gael MartinChristian Robert
 
SPDE presentation 2012
SPDE presentation 2012SPDE presentation 2012
SPDE presentation 2012Zheng Mengdi
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Valentin De Bortoli
 
Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...
Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...
Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...Frank Nielsen
 
Graph Kernels for Chemical Informatics
Graph Kernels for Chemical InformaticsGraph Kernels for Chemical Informatics
Graph Kernels for Chemical InformaticsMukund Raj
 

Ähnlich wie Patch Matching with Polynomial Exponential Families and Projective Divergences (20)

Slides: A glance at information-geometric signal processing
Slides: A glance at information-geometric signal processingSlides: A glance at information-geometric signal processing
Slides: A glance at information-geometric signal processing
 
Thesis defense
Thesis defenseThesis defense
Thesis defense
 
k-MLE: A fast algorithm for learning statistical mixture models
k-MLE: A fast algorithm for learning statistical mixture modelsk-MLE: A fast algorithm for learning statistical mixture models
k-MLE: A fast algorithm for learning statistical mixture models
 
Murphy: Machine learning A probabilistic perspective: Ch.9
Murphy: Machine learning A probabilistic perspective: Ch.9Murphy: Machine learning A probabilistic perspective: Ch.9
Murphy: Machine learning A probabilistic perspective: Ch.9
 
Slides: Hypothesis testing, information divergence and computational geometry
Slides: Hypothesis testing, information divergence and computational geometrySlides: Hypothesis testing, information divergence and computational geometry
Slides: Hypothesis testing, information divergence and computational geometry
 
QMC: Operator Splitting Workshop, Proximal Algorithms in Probability Spaces -...
QMC: Operator Splitting Workshop, Proximal Algorithms in Probability Spaces -...QMC: Operator Splitting Workshop, Proximal Algorithms in Probability Spaces -...
QMC: Operator Splitting Workshop, Proximal Algorithms in Probability Spaces -...
 
Slides: The dual Voronoi diagrams with respect to representational Bregman di...
Slides: The dual Voronoi diagrams with respect to representational Bregman di...Slides: The dual Voronoi diagrams with respect to representational Bregman di...
Slides: The dual Voronoi diagrams with respect to representational Bregman di...
 
Low rank tensor approximation of probability density and characteristic funct...
Low rank tensor approximation of probability density and characteristic funct...Low rank tensor approximation of probability density and characteristic funct...
Low rank tensor approximation of probability density and characteristic funct...
 
Computational Information Geometry on Matrix Manifolds (ICTP 2013)
Computational Information Geometry on Matrix Manifolds (ICTP 2013)Computational Information Geometry on Matrix Manifolds (ICTP 2013)
Computational Information Geometry on Matrix Manifolds (ICTP 2013)
 
QMC Error SAMSI Tutorial Aug 2017
QMC Error SAMSI Tutorial Aug 2017QMC Error SAMSI Tutorial Aug 2017
QMC Error SAMSI Tutorial Aug 2017
 
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
 
MUMS Opening Workshop - An Overview of Reduced-Order Models and Emulators (ED...
MUMS Opening Workshop - An Overview of Reduced-Order Models and Emulators (ED...MUMS Opening Workshop - An Overview of Reduced-Order Models and Emulators (ED...
MUMS Opening Workshop - An Overview of Reduced-Order Models and Emulators (ED...
 
Testing for mixtures by seeking components
Testing for mixtures by seeking componentsTesting for mixtures by seeking components
Testing for mixtures by seeking components
 
Pattern learning and recognition on statistical manifolds: An information-geo...
Pattern learning and recognition on statistical manifolds: An information-geo...Pattern learning and recognition on statistical manifolds: An information-geo...
Pattern learning and recognition on statistical manifolds: An information-geo...
 
Bayesian inference on mixtures
Bayesian inference on mixturesBayesian inference on mixtures
Bayesian inference on mixtures
 
Workshop in honour of Don Poskitt and Gael Martin
Workshop in honour of Don Poskitt and Gael MartinWorkshop in honour of Don Poskitt and Gael Martin
Workshop in honour of Don Poskitt and Gael Martin
 
SPDE presentation 2012
SPDE presentation 2012SPDE presentation 2012
SPDE presentation 2012
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...
 
Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...
Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...
Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...
 
Graph Kernels for Chemical Informatics
Graph Kernels for Chemical InformaticsGraph Kernels for Chemical Informatics
Graph Kernels for Chemical Informatics
 

Kürzlich hochgeladen

Environmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial BiosensorEnvironmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial Biosensorsonawaneprad
 
User Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather StationUser Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather StationColumbia Weather Systems
 
Pests of safflower_Binomics_Identification_Dr.UPR.pdf
Pests of safflower_Binomics_Identification_Dr.UPR.pdfPests of safflower_Binomics_Identification_Dr.UPR.pdf
Pests of safflower_Binomics_Identification_Dr.UPR.pdfPirithiRaju
 
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxmaryFF1
 
OECD bibliometric indicators: Selected highlights, April 2024
OECD bibliometric indicators: Selected highlights, April 2024OECD bibliometric indicators: Selected highlights, April 2024
OECD bibliometric indicators: Selected highlights, April 2024innovationoecd
 
preservation, maintanence and improvement of industrial organism.pptx
preservation, maintanence and improvement of industrial organism.pptxpreservation, maintanence and improvement of industrial organism.pptx
preservation, maintanence and improvement of industrial organism.pptxnoordubaliya2003
 
Topic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxTopic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxJorenAcuavera1
 
Four Spheres of the Earth Presentation.ppt
Four Spheres of the Earth Presentation.pptFour Spheres of the Earth Presentation.ppt
Four Spheres of the Earth Presentation.pptJoemSTuliba
 
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdfPests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdfPirithiRaju
 
basic entomology with insect anatomy and taxonomy
basic entomology with insect anatomy and taxonomybasic entomology with insect anatomy and taxonomy
basic entomology with insect anatomy and taxonomyDrAnita Sharma
 
Forensic limnology of diatoms by Sanjai.pptx
Forensic limnology of diatoms by Sanjai.pptxForensic limnology of diatoms by Sanjai.pptx
Forensic limnology of diatoms by Sanjai.pptxkumarsanjai28051
 
Citronella presentation SlideShare mani upadhyay
Citronella presentation SlideShare mani upadhyayCitronella presentation SlideShare mani upadhyay
Citronella presentation SlideShare mani upadhyayupadhyaymani499
 
《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》rnrncn29
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.PraveenaKalaiselvan1
 
Neurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trNeurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trssuser06f238
 
Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...navyadasi1992
 
Pests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdfPests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdfPirithiRaju
 
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTXALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTXDole Philippines School
 
User Guide: Magellan MX™ Weather Station
User Guide: Magellan MX™ Weather StationUser Guide: Magellan MX™ Weather Station
User Guide: Magellan MX™ Weather StationColumbia Weather Systems
 

Kürzlich hochgeladen (20)

Environmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial BiosensorEnvironmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial Biosensor
 
User Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather StationUser Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather Station
 
Pests of safflower_Binomics_Identification_Dr.UPR.pdf
Pests of safflower_Binomics_Identification_Dr.UPR.pdfPests of safflower_Binomics_Identification_Dr.UPR.pdf
Pests of safflower_Binomics_Identification_Dr.UPR.pdf
 
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
 
OECD bibliometric indicators: Selected highlights, April 2024
OECD bibliometric indicators: Selected highlights, April 2024OECD bibliometric indicators: Selected highlights, April 2024
OECD bibliometric indicators: Selected highlights, April 2024
 
preservation, maintanence and improvement of industrial organism.pptx
preservation, maintanence and improvement of industrial organism.pptxpreservation, maintanence and improvement of industrial organism.pptx
preservation, maintanence and improvement of industrial organism.pptx
 
Topic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxTopic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptx
 
Four Spheres of the Earth Presentation.ppt
Four Spheres of the Earth Presentation.pptFour Spheres of the Earth Presentation.ppt
Four Spheres of the Earth Presentation.ppt
 
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdfPests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdf
 
basic entomology with insect anatomy and taxonomy
basic entomology with insect anatomy and taxonomybasic entomology with insect anatomy and taxonomy
basic entomology with insect anatomy and taxonomy
 
Forensic limnology of diatoms by Sanjai.pptx
Forensic limnology of diatoms by Sanjai.pptxForensic limnology of diatoms by Sanjai.pptx
Forensic limnology of diatoms by Sanjai.pptx
 
Citronella presentation SlideShare mani upadhyay
Citronella presentation SlideShare mani upadhyayCitronella presentation SlideShare mani upadhyay
Citronella presentation SlideShare mani upadhyay
 
《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
 
Neurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trNeurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 tr
 
Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...
 
Pests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdfPests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdf
 
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTXALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
 
User Guide: Magellan MX™ Weather Station
User Guide: Magellan MX™ Weather StationUser Guide: Magellan MX™ Weather Station
User Guide: Magellan MX™ Weather Station
 
Volatile Oils Pharmacognosy And Phytochemistry -I
Volatile Oils Pharmacognosy And Phytochemistry -IVolatile Oils Pharmacognosy And Phytochemistry -I
Volatile Oils Pharmacognosy And Phytochemistry -I
 

Patch Matching with Polynomial Exponential Families and Projective Divergences

  • 1. Patch matching with polynomial exponential families and projective divergences Frank Nielsen 1 Richard Nock2 1École Polytechnique & Sony CSL 2Data61 & Australian National University 9th Similarity Search and Applications
  • 2. 1/27 The “Patch Matching” problem Given a query patch, patch matching = finding “similar” patches in a target image. Handle noise, symmetry [16, 19], zoom, smooth deformation, etc.
  • 3. 2/27 Patch Matching: Baseline (naïve) algorithm Sum of Square Differences (SSDs) of the pixel intensities: D(Is, It(x0)) = x∈[1,ws ]×[1,hs ] (Is(x) − It(x + x0))2 (= squared Euclidean distance on vectorized patch intensities) but small image shift can cause large 2 2 distance shift [18] Naïve brute-force algorithm in O(wthtwshs) too time consuming! → extend to multiple color channels with sum/max Alternative method: Fourier phase correlation method [11, 8] in O(wh log(wh)) but limited to translations Factorize computations using Nearest Neighbor Fields [3, 4] (+ GPU)
  • 4. 3/27 Large patch PM application: Zoom stitching Nested image mosaicing: one image is a patch fully contained inside another image
  • 5. 4/27 Experiments: brute-force baseline algorithm Image of size 1280, patch of size 120 × 120 SSD 30.7 sec SSDRGBSum 96.7 sec SSDRGBMax 208.7 sec HP Elitebook 840 G1 (i7-4600U CPU 2.1 GHz with 8 GB RAM)
  • 6. 5/27 Experiments for the baseline algorithm HP Elitebook 840 G1 (i7-4600U CPU 2.1 GHz with 8 GB RAM) Complexity O(wthtwshs) does not scale! image size 500 × 300 960 × 640 1500 × 1000 patch size 50 × 50 0.82 3.70 8.83 100 × 100 1.31 8.81 20.34 200 × 200 0.79 15.34 66.70 SSDRGBSum (in sec): image size 500 × 300 960 × 640 1500 × 1000 patch size 50 × 50 2.20 11.63 19.95 100 × 100 3.88 23.68 63.71 200 × 200 2.22 43.14 161.51
  • 7. 6/27 Our proposed method: PEF-PM Polynomial Exponential Family-Patch Matching
  • 8. 7/27 PEF-PM: Polynomial Exponential Family-PM Polynomial exponential family: p(x; θ) = exp( D i=1 θi xi − F(θ)) t(x) = (x1, . . . , xD) = sufficient statistics [5, 1], θ = natural parameters. x, y = x y ∈ R = Euclidean inner product. F(θ) = log exp( θ, t(x) )dx = log-normalizer → However F = log exp( θ, t(x) )dx not available in closed-form! Estimate θ using Score Matching Estimator [10] (SME, instead of Maximum Likelihood Estimator, MLE) Define projective distance D between PEFs to cope with unnormalized distributions: D(λq, λ q ) = D(q, q ) for any λ, λ > 0 Accelerate batched SMEs using integral images = Summed Area Tables (SATs)
  • 9. 8/27 Score Matching Estimator [10] (SME) for PEFs Divergence estimator: minimize the Fisher divergence: J(p : q) = 1 2 d i=1 ∂ log p(x) ∂xi − ∂ log q(x) ∂xi 2 p(x)dx, with J(p : q) = 0 iff p = λq for λ > 0. Fisher divergence is one-sided projective divergence: J(p : λq) = J(p : q). For univariate Polynomial Exponential Families, SME: θSM(s(x)) = − (Es[A(x)])−1 (Es[b(x)]) where A(x) = [ti (x)tj (x)] (D × D symmetric matrix) and b(x) = [t1 (x) . . . tD(x)] (D-dimensional column vector). For PEFs, ti (x) = ixi−1 and ti (x) = i(i − 1)xi−2, and therefore A = Es[A(x)] = [aij = ijMi+j−2(s)] and b = Es[b(x)] = [bj = j(j − 1)Mj−2(s)], where Ml (s) = 1 s i xl i is the l-th sample raw moment.
  • 10. 9/27 Accelerating batched SMEs for PEFs using SATs To perform Score Matching in OD(1), use SATs: Summed Area Tables [7] (SATs), also called integral images: ∀(x, y), F(x, y) = x ≤x,y ≤y f (x , y ) Single pass computation in preprocessing Then patch PEF SME (f = t , t , a rectangle bottom-left corner n(x0, y0) and top-right corner (x1, y1)) in O(1) time: x0≤x≤x1,y0≤y≤y1 f (x, y) = F(x1, y1)+F(x0, y0)−F(x0, y1)−F(x1, y0)
  • 11. 10/27 Similarity between PEFs: Projective divergences Relative entropy called the Kullback-Leibler divergence: KL(p(x; θs), p(x; θt)) = x∈R+ p(x; θs) log p(x; θs) p(x; θt) dx amounts to Bregman divergence for exponential families [2], but need F in closed-form. Projective γ-divergence [9, 15, 6] (for γ > 0): Dγ(λq, λ q ) = Dγ(q, q ) for any λ, λ > 0 Dγ(p, q) = 1 γ(γ − 1) log pγ(x)q1−γ(x)dx) ( p(x)dx)γ( q(x)dx)1−γ Dγ(p, q) = 1 γ(1 + γ) log Iγ(p, p) − 1 γ log Iγ(p, q) + 1 1 + γ log Iγ(q, q) where Iγ(p, q) = x∈X p(x)q(x)γ dx.
  • 12. 11/27 Projective γ-divergences for exponential families Use the symmetrized γ-divergence Sγ for patch similarity. When γ → 0, Dγ(p, q) → KL(p, q) (Bregman divergence for EFs) Iγ(θp, θq) = exp (F(θp + γθq) − F(θp) − γF(θq)) . Provided that the γθp + θq ∈ Θ. Condition always satisfied when the natural parameter space [12, 14, 13] is a cone (since γ > 0), like the multivariate Gaussians distributions, the multinomial distributions, and the Wishart distributions, just to name a few.
  • 13. 12/27 Monte-Carlo stochastic estimation of Sγ Although projective divergence, exact Dγ depends on the untractable log-normalizer! Approximate Iγ(p, q) by discretizing the integral using quadrature rules Monte-Carlo stochastic integration (γ = 0.1, s = 100000): Iγ(p, q) = x∈X p(x)q(x)γ dx 1 m m i=1 q(xi )γ with x1, ..., xs ∼ p(x) (iid) → Sample variance, confidence interval (CI) of Monte-Carlo estimator.
  • 14. 13/27 Results of PEF-PM Impact of the polynomial degree of PEFs, the order D of the exponential family order D = 3 order D = 4 order D = 5 order D = 6 Image size 1280 × 853, patch size 100 × 100
  • 15. 14/27 Profiling PEF-PM timings Computational time in seconds for PEFs. degree of PEF 2 3 4 5 6 SAT construction 5.99 6.37 8.04 9.56 11.86 PEF estimation (SM) 5.24 7.44 8.96 12.84 14.82 Sγ search 7.02 8.86 9.70 10.30 10.52 Baseline: image size 500 × 300 960 × 640 1500 × 1000 patch size 50 × 50 0.82 3.70 8.83 100 × 100 1.31 8.81 20.34 200 × 200 0.79 15.34 66.70
  • 16. 15/27 PEFs handles patch symmetries (→ bag of pixels) Patch matching with symmetry (reflection) detected by PEF-PM of order 6 patch size 250 × 250, image dimension (960, 640)
  • 17. 16/27 Summary of contributions Model patch colors using Polynomial Exponential Families (PEFs), universal smooth (positive) densities Estimate PEFs using Score Matching Estimator, and accelerate the batch estimator using Summed Area Tables (SATs) Use a statistical projective divergence: the symmetrized γ-divergence. Closed-form expression for EFs with log-normalizer F Monte-Carlo estimation without explicit log-normalizer Handle noise robustly (γ-divergence), symmetries (color distributions), etc. (see paper)
  • 18. 17/27 From a historical view of statistical distances...
  • 19. 18/27 ... To a structural view of classes of distances If (P : Q) = p(x)f (q(x) p(x) dν(x) BF (P : Q) = F(P) − F(Q) − P − Q, F(Q) tBF (P : Q) = BF (P :Q) √ 1+ F (Q) 2 CD,g(P : Q) = g(Q)D(P : Q) BF,g(P : Q; W) = WBF P Q : Q W Dv (P : Q) = D(v(P) : v(Q)) v-Divergence Dv total Bregman divergence tB(· : ·) Bregman divergence BF (· : ·) conformal divergence CD,g(· : ·) Csisz´ar f-divergence If (· : ·) scaled Bregman divergence BF (· : ·; ·) scaled conformal divergence CD,g(· : ·; ·) Dissimilarity measure Divergence Projective divergence γ-divergence H¨yvarinen SM/RM D(λp : λ p ) = D(p : p ) D(λp : p ) = D(p : p ) one-sided double sided C3 Axiomatic approach, exhausitivity characteristics
  • 20. 19/27 Edited books: 2012 2014 2016 3rd edition GSI’17: www.gsi2017.org Geometric Sciences of Information, Paris, Fall 2017
  • 21. 20/27 Thank you Acknowledgments: We gratefully thank Quei-An Chen (École Polytechnique, France) for implementing our patch matching system and performing various experiments.
  • 22. 21/27 References I S.-i. Amari. Information Geometry and Its Applications. Applied Mathematical Sciences. Springer Japan, 2016. Arindam Banerjee, Srujana Merugu, Inderjit S Dhillon, and Joydeep Ghosh. Clustering with Bregman divergences. The Journal of Machine Learning Research, 6:1705–1749, 2005. Connelly Barnes, Eli Shechtman, Adam Finkelstein, and Dan B Goldman. Patchmatch: a randomized correspondence algorithm for structural image editing. ACM Transactions on Graphics (TOG), 28(3):24, 2009. Connelly Barnes, Eli Shechtman, Dan B Goldman, and Adam Finkelstein. The generalized patchmatch correspondence algorithm. In European Conference on Computer Vision (ECCV), pages 29–43. Springer, 2010. Lawrence D Brown. Fundamentals of statistical exponential families with applications in statistical decision theory. Lecture Notes-monograph series, 9:i–279, 1986. Ting-Li Chen, Dai-Ni Hsieh, Hung Hung, I-Ping Tu, Pei-Shien Wu, Yi-Ming Wu, Wei-Hau Chang, Su-Yun Huang, et al. γ-sup: A clustering algorithm for cryo-electron microscopy images of asymmetric particles. The Annals of Applied Statistics, 8(1):259–285, 2014. Franklin C Crow. Summed-area tables for texture mapping. ACM SIGGRAPH computer graphics, 18(3):207–212, 1984.
  • 23. 22/27 References II Hassan Foroosh, Josiane B Zerubia, and Marc Berthod. Extension of phase correlation to subpixel registration. IEEE Transactions onImage Processing, 11(3):188–200, 2002. Hironori Fujisawa and Shinto Eguchi. Robust parameter estimation with a small bias against heavy contamination. Journal of Multivariate Analysis, 99(9):2053–2081, 2008. Aapo Hyvärinen. Estimation of non-normalized statistical models by score matching. Journal of Machine Learning Research, 6(Apr):695–709, 2005. CD Kuglin. The phase correlation image alignment method. In Proc. Int. Conf. on Cybernetics and Society, 1975, pages 163–165, 1975. Frank Nielsen. Closed-form information-theoretic divergences for statistical mixtures. In Pattern Recognition (ICPR), 21st International Conference on, pages 1723–1726. IEEE, 2012. Frank Nielsen and Richard Nock. A closed-form expression for the Sharma-Mittal entropy of exponential families. Journal of Physics A: Mathematical and Theoretical, 45(3):032003, 2011. Frank Nielsen and Richard Nock. On the chi square and higher-order chi distances for approximating f -divergences. IEEE Signal Processing Letters, 1(21):10–13, 2014. Akifumi Notsu, Osamu Komori, and Shinto Eguchi. Spontaneous clustering via minimum gamma-divergence. Neural computation, 26(2):421–448, 2014.
  • 24. 23/27 References III Viorica Patraucean, Rafael Gioi, and Maks Ovsjanikov. Detection of mirror-symmetric image patches. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 211–216, 2013. Carsten Rother, Vladimir Kolmogorov, and Andrew Blake. Grabcut: Interactive foreground extraction using iterated graph cuts. ACM transactions on graphics (TOG), 23(3):309–314, 2004. Lucas Theis, Aäron van den Oord, and Matthias Bethge. A note on the evaluation of generative models. arXiv preprint arXiv:1511.01844, 2015. ICLR 2016. Z. Wang, Z. Tang, and X. Zhang. Reflection symmetry detection using locally affine invariant edge correspondence. IEEE Transactions on Image Processing, 24(4):1297–1301, April 2015.
  • 25. 24/27 Perspectives and future work Model selection of the polynomial exponential family according to the query patch Foreground/background detection in patches (say, using Grabcut [17]) and matching only the foreground statistical distributions to improve the accuracy of patch matching. Modeling by distributions allows us to discard rectangular windows. Multivariate PEFs to bypass sum/max of univariate PEF color channel distances Handle clamped support [0, 255] instead of [0, +∞)
  • 26. 25/27 Qualitative results of PEF-PM patch size 150 × 150 and image size 960 × 640 aligned pixel-based (SSD) PEF (D = 4) with Sγ Intensity Sum SSD
  • 28. 27/27 Acceptance-rejection sampling for PEFs f (x) ∝ ePθ(x) with polynomial P(x) = D i=1 θi xi , θ = (θ1, ..., θD) defined on support X = [0, 255]. Computationally intractable normalizer Z(θ) = x∈X ePθ(x)dx. Proposal distribution g(y) = 1 255 , uniform density on X f (x) ≤ Mθg(x) for Mθ = 255 exp(maxx∈X Pθ(x)). maxx∈X Pθ(x) ≤ D i=1 maxx∈X θi xi = D i=1(θi 255i )+. In particular, Mθ = 255 when ∀i, θi ≤ 0. Draw variate u ∼ Unif(0, 1) and variate y ∼ Unif(0, 255). If u < f (y) Mθg(y) accept y as variate of f (x), otherwise reject it. Expected M iterations for drawing a variate of f (x)