Bilevel Sparse Coding

Size: px
Start display at page:

Download "Bilevel Sparse Coding"

Transcription

1 Adobe Research 345 Park Ave, San Jose, CA Mar 15, 2013

2 Outline 1 2 The learning model The learning algorithm 3 4

3 Sparse Modeling Many types of sensory data, e.g., images and audio, are in high-dimensional spaces, but with low-intrinsic dimensions Sparse representation in some domain. Simple model, effective prior.

4 Sparse Modeling Many types of sensory data, e.g., images and audio, are in high-dimensional spaces, but with low-intrinsic dimensions Sparse representation in some domain. Simple model, effective prior. Sparse representation: represent data in the most parsimonious terms x = Dz, where x R d, D R d K, and z 0 d.

5 Sparse Modeling Many types of sensory data, e.g., images and audio, are in high-dimensional spaces, but with low-intrinsic dimensions Sparse representation in some domain. Simple model, effective prior. Sparse representation: represent data in the most parsimonious terms x = Dz, where x R d, D R d K, and z 0 d. Sparsity: driving factor for broad applications Compressive sensing, low-rank matrices, etc. Compression, denoising, deblurring, super-resolution, etc. Recognition, subspace clustering, deep learning, etc.

6 Sparse Coding Quest for Dictionary Signals are normally mixtures of diverse phenomena; how can we wisely choose D to perform well on the given signals?

7 Sparse Coding Quest for Dictionary Signals are normally mixtures of diverse phenomena; how can we wisely choose D to perform well on the given signals? A data driven solution: train adaptive dictionaries from the given signal instances for sparse representations.

8 Sparse Coding Quest for Dictionary Signals are normally mixtures of diverse phenomena; how can we wisely choose D to perform well on the given signals? A data driven solution: train adaptive dictionaries from the given signal instances for sparse representations. Given training data {x i } N i=1, the dictionary learning problem, in its most popular form, can be formulated as min D,{α i } N i=1 N x i Dα i λ α i 1, s.t. D(:, j) 2 1, i=1 where D R d K (d < K ) is an over-complete dictionary.

9 Sparse Coding Quest for Dictionary Signals are normally mixtures of diverse phenomena; how can we wisely choose D to perform well on the given signals? A data driven solution: train adaptive dictionaries from the given signal instances for sparse representations. Given training data {x i } N i=1, the dictionary learning problem, in its most popular form, can be formulated as min D,{α i } N i=1 N x i Dα i λ α i 1, s.t. D(:, j) 2 1, i=1 where D R d K (d < K ) is an over-complete dictionary. Problem: it only cares about low-level sparse reconstruction, not the high-level task!

10 Quest for Dictionary Many vision and learning tasks can be formulated based on sparse representations Image feature learning Image super-resolution Compressive sensing Image classification, etc

11 Quest for Dictionary Many vision and learning tasks can be formulated based on sparse representations Image feature learning Image super-resolution Compressive sensing Image classification, etc We relate the low-level dictionary learning with the high-level task naturally with a bilevel formulation.

12 Quest for Dictionary Many vision and learning tasks can be formulated based on sparse representations Image feature learning Image super-resolution Compressive sensing Image classification, etc We relate the low-level dictionary learning with the high-level task naturally with a bilevel formulation. Goal: learn more meaningful sparse representation for the given task.

13 Quest for Dictionary Many vision and learning tasks can be formulated based on sparse representations Image feature learning Image super-resolution Compressive sensing Image classification, etc We relate the low-level dictionary learning with the high-level task naturally with a bilevel formulation. Goal: learn more meaningful sparse representation for the given task. Advantage: the training procedure is totally consistent with the testing objective.

14 Bilevel optimization Mathematical programs with optimization problems in the constraints: min x X,y F (x, y) s.t. G(x, y) 0, y = arg min y s.t. g(x, y) 0. f (x, y), F and f are the upper-level and lower-level objective functions respectively. G and g are the upper-level and lower-level constraints respectively.

15 Bilevel optimization Simple example: Toll-setting problem on a transportation network Network manager maximizes the revenue raised from tolls Network users minimize their travel costs T a x a max T,f,x s.t. a Ā l a T a u a, a Ā (f, x) arg min c a x f,x a + T a x a a A a Ā s.t....

16 : Outline The learning model The learning algorithm 1 2 The learning model The learning algorithm 3 4

17 The Learning Model The learning model The learning algorithm A generic bilevel learning model: min D,Θ 1 N N L(D, z i, Θ) i=1 s.t. z i = arg min α 1, s.t. x i Dα 2 2 ɛ, i, α G(Θ) 0, D(:, k) 2 1, k. L is some smooth cost function defined by the specific task. Θ is the parameter set of a specific model. {x i } N i=1 are training samples from the input space X. May involve more than one feature space.

18 A Simple Example The learning model The learning algorithm Coupled sparse coding: Relate two feature spaces by their common sparse representations. 1 min D x,d y N s.t. z x i N z x i z y i 2 2 i=1 = arg min α 1, s.t. x i D x α 2 2 ɛ x, i, α z y i = arg min α 1, s.t. y i D y α 2 2 ɛ y, i, α D x (:, k) 2 1, k, D y (:, k) 2 1, k, where {x i, y i } N i=1 are randomly sampled from the joint space X Y.

19 : Outline The learning model The learning algorithm 1 2 The learning model The learning algorithm 3 4

20 A Difficult Problem The learning model The learning algorithm Bilevel optimization: mathematical programs with optimization problems in the constraints min D,Θ 1 N N L(D, z i, Θ) i=1 s.t. z i = arg min α 1, s.t. x i Dα 2 2 ɛ, i, α G(Θ) 0, D(:, k) 2 1, k. Optimization for D is a bilevel optimization. L is the upper-level objective and l 1 -norm minimization is the lower-level optimization. Highly nonconvex and highly nonlinear.

21 Descent Method? The learning model The learning algorithm Regard z as an implicit function of D in the lower-level problem, the bilevel program can be viewed solely in terms of the upper-level variable D.

22 Descent Method? The learning model The learning algorithm Regard z as an implicit function of D in the lower-level problem, the bilevel program can be viewed solely in terms of the upper-level variable D. Applying the chain rule, we have, whenever D z(d) is well defined D L(D, z(d), Θ) = D L(D, z, Θ) + z L(D, z, Θ) D z(d).

23 Descent Method? The learning model The learning algorithm Regard z as an implicit function of D in the lower-level problem, the bilevel program can be viewed solely in terms of the upper-level variable D. Applying the chain rule, we have, whenever D z(d) is well defined D L(D, z(d), Θ) = D L(D, z, Θ) + z L(D, z, Θ) D z(d). Problem: Is the gradient D z(d) available? z = arg min α α 1, s.t. x Dα 2 2 ɛ.

24 Differentiability The learning model The learning algorithm Lasso The l 1 -norm minimization problem can be reformulated as the Lasso problem z = arg min α x Dα λ α 1. Transition Point (Efron et al. 2004) For a given response vector x, there is a finite sequence of λ s, λ 0 > λ 1 > > λ K = 0, such that if λ is in the interval of (λ m, λ m+1 ), the active set Λ = {k : z(k) 0} and sign vector sign(z Λ ) are constant with respect to λ.

25 Differentiability The learning model The learning algorithm Theorem Fix any λ > 0, and λ is not a transition point for x, the active set Λ and the sign vector sign(z Λ ) are locally constant with respect to both x and D.

26 Differentiability The learning model The learning algorithm If λ is not a transition point of x, we have the equiangular conditions a : x Dz λ sign(z(k)) = 0, for k Λ, z(k) b : x Dz 2 2 z(k) < λ, for k Λ.

27 Differentiability The learning model The learning algorithm If λ is not a transition point of x, we have the equiangular conditions a : x Dz λ sign(z(k)) = 0, for k Λ, z(k) b : x Dz 2 2 z(k) < λ, for k Λ. Applying implicit differentiation on the above Eqn. (a), we have z Λ = ( ( D T ) 1 D T Λ x D ΛD Λ Λ D Λ DT Λ D ) Λ z Λ. D Λ

28 Differentiability The learning model The learning algorithm Let Ω denotes the nonactive set, we observe that As z Λ is only connected with D Λ, a perturbation on D Ω will not change its value. Therefore, we have z Λ D Ω = 0. (1) As Λ and sign(z Λ ) are constant for a small perturbation of D, z Ω stays zero, so we have z Ω D = 0 (2)

29 Differentiability The learning model The learning algorithm Let Ω denotes the nonactive set, we observe that As z Λ is only connected with D Λ, a perturbation on D Ω will not change its value. Therefore, we have z Λ D Ω = 0. (1) As Λ and sign(z Λ ) are constant for a small perturbation of D, z Ω stays zero, so we have z Ω D = 0 (2) Therefore, the nonzero part of D z(d) is defined by z Λ / D Λ.

30 Stochastic Gradient Descent The learning model The learning algorithm Given D z(d), D L can be evaluated. Applying stochastic gradient descent, we have L n D n+1 = D n r n D / L n D 2 r 0 r n = (n/n + 1) p, where p controls the shrinkage rate the step size.

31 Stochastic Gradient Descent The learning model The learning algorithm Given D z(d), D L can be evaluated. Applying stochastic gradient descent, we have L n D n+1 = D n r n D / L n D 2 r 0 r n = (n/n + 1) p, where p controls the shrinkage rate the step size. Project the updated dictionary onto the unit ball. The complete optimization procedure alternatively optimize over D and Θ.

32 : Outline 1 2 The learning model The learning algorithm 3 4

33 Single Frame Super-resolution Problem: Given a single low-resolution input, and a set of pairs (high- and low-resolution) of training patches sampled from similar images, reconstruct a high-resolution version of the input. Applications Photo zooming (e.g., Photoshop, Genuine Fractal) Photo printing Video standard conversion, etc Difficulty: single-image super-resolution is an extremely ill-posed problem.

34 Super-resolution via Sparse Recovery High-resolution patches have sparse representations in terms of some over-complete dictionary x = D h z 0 where x R m, D h R m K, and z 0 0 m

35 Super-resolution via Sparse Recovery High-resolution patches have sparse representations in terms of some over-complete dictionary x = D h z 0 where x R m, D h R m K, and z 0 0 m We do not observe the high-resolution patch x, but its low-resolution version y R n y = Lx = LD h z 0 = D l z 0 L is the sampling matrix (blurring and downsampling) y is the n linear measurements of the sparse coefficients z 0

36 Super-resolution via Sparse Recovery High-resolution patches have sparse representations in terms of some over-complete dictionary x = D h z 0 where x R m, D h R m K, and z 0 0 m We do not observe the high-resolution patch x, but its low-resolution version y R n y = Lx = LD h z 0 = D l z 0 L is the sampling matrix (blurring and downsampling) y is the n linear measurements of the sparse coefficients z 0 Sparse recovery? If we can obtain z 0 from y = D l z (underdetermined linear system), we can recover x as D h z 0.

37 Super-resolution via Sparse Recovery Assume we have the coupled dictionaries D h and D l. Input: low-resolution image Y.

38 Super-resolution via Sparse Recovery Assume we have the coupled dictionaries D h and D l. Input: low-resolution image Y. Find sparse solution for each patch y p of Y by z 0 = arg min z D l z y p λ z 1.

39 Super-resolution via Sparse Recovery Assume we have the coupled dictionaries D h and D l. Input: low-resolution image Y. Find sparse solution for each patch y p of Y by z 0 = arg min z D l z y p λ z 1. Recover the corresponding high-resolution image patch as x p = D h z 0.

40 Super-resolution via Sparse Recovery Assume we have the coupled dictionaries D h and D l. Input: low-resolution image Y. Find sparse solution for each patch y p of Y by z 0 = arg min z D l z y p λ z 1. Recover the corresponding high-resolution image patch as x p = D h z 0. How to train D l and D h for good recovery?

41 Joint Dictionary Training Previous Approach Our previous solution. Randomly sample high- and low-resolution image patch pairs {x i, y i } N i=1 from the training data. Learn D h, D l jointly: min D h,d l,{z i } N x i D h z i y i D l z i λ z i 1, i=1 s.t. D h (:, k) 2 1, D l (:, k) 2 1

42 Joint Dictionary Training Previous Approach Our previous solution. Randomly sample high- and low-resolution image patch pairs {x i, y i } N i=1 from the training data. Learn D h, D l jointly: min D h,d l,{z i } N x i D h z i y i D l z i λ z i 1, i=1 s.t. D h (:, k) 2 1, D l (:, k) 2 1 However,...

43 Joint Dictionary Training Problem In training, we have min D h,d l,{z i } N x i D h z i y i D l z i λ z i 1 i=1

44 Joint Dictionary Training Problem In training, we have min D h,d l,{z i } N x i D h z i y i D l z i λ z i 1 i=1 In testing, we only have the low-resolution patch y i, min zi x i D h z i 2 2+ y i D l z i λ z i 1, and therefore, good reconstruction of x i is not guaranteed.

45 Bilevel Formulation Goal: Learn D h and D l, such that the sparse representation z of y in terms of D l can well reconstruct x with D h.

46 Bilevel Formulation Goal: Learn D h and D l, such that the sparse representation z of y in terms of D l can well reconstruct x with D h. Given high- and low-resolution training patch pairs {x i, y i } N i=1, the learning model is formulated as 1 min D h,d l N N D h z i x i 2 2 i=1 s.t. z i = arg min α 1, s.t. y i D l α 2 2 ɛ α D l (:, k) 2 1, D h (:, k) 2 1,

47 Bilevel Formulation Goal: Learn D h and D l, such that the sparse representation z of y in terms of D l can well reconstruct x with D h. Given high- and low-resolution training patch pairs {x i, y i } N i=1, the learning model is formulated as 1 min D h,d l N N D h z i x i 2 2 i=1 s.t. z i = arg min α 1, s.t. y i D l α 2 2 ɛ α D l (:, k) 2 1, D h (:, k) 2 1, The training process is completely consist with testing.

48 Results Setting: 100, 000 high- and low-resolution 5 5 image patch pairs are sampled for training and 100, 000 for testing. D h and D l are initialized from joint dictionary training. The learning algorithm converges in 5 iterations % 19.60% 21.89% 18.91% 20.55% % 15.75% 17.92% 15.69% 14.70% % 16.96% 19.95% 17.57% 15.99% % 17.78% 18.30% 16.80% 15.82% % 14.68% 15.52% 14.64% 20.51% Pixel-wise MSE reduction compared with joint dictionary training

49 SR Results Visual comparison: Top: joint dictionary training; bottom: bilevel sparse coding.

50 Practical Implementation Learn fast sparse coding approximations with a neural network. Selective patch processing. Takes 5s to upscale an image from to on a single core 3 GHz with 4G RAM. One of the fastest SR algorithms. Input

51 Practical Implementation Learn fast sparse coding approximations with a neural network. Selective patch processing. Takes 5s to upscale an image from to on a single core 3 GHz with 4G RAM. One of the fastest SR algorithms. Bicubic

52 Practical Implementation Learn fast sparse coding approximations with a neural network. Selective patch processing. Takes 6s to upscale an image from to on a single core 3 GHz with 4G RAM. One of the fastest SR algorithms. Ours

53 : Outline 1 2 The learning model The learning algorithm 3 4

54 Feature Representation by Pooling Sparse Codes Fig. The image feature extraction diagram.

55 Feature Representation by Pooling Sparse Codes A simple two-layer network. Coding: VQ, soft assignment, LLC, sparse coding, linear filtering. Pooling: average, energy, max, log, l p. Works well on diverse recognition benchmarks: object, scene, action, face, digit, gender, expression, age estimation, and so on. Key component of the winner system for PASCAL09 on image recognition. Image feature extraction diagram

56 The Feature Extraction Algorithm 1 Represent image X as sets of local descriptors in a spatial pyramid X = [ Y 0 11, Y1 11, Y 1 12,..., Y 2 44], 2 Given dictionary D, encode the local descriptors into sparse codes by Ẑ s ij = arg min Y s ij DA λ A 1, A and we obtain S = [Ẑ0 11, Ẑ1 11, Ẑ2 12,..., 44] Ẑ2 3 Max pooling over each set of sparse codes and concatenate them β = 2 s=0 2 s i,j=1 [ ] β s ij, where βij s ( Ẑs ) = max ij.

57 Unsupervised Dictionary Learning Randomly sample a set of local descriptors {x i } N i=1 from the training set, use current sparse coding technique to learn a dictionary D that can sparsely represent the data. min D,{α i } N i=1 n x i Dα i λ α i 1, i=1 s.t. D(:, k) 2 1, Optimization is performed in an alternating fashion: fix D, optimize {α i } N i=1 ; and fix {α i} N i=1, and optimize D.

58 Supervised Dictionary Learning The unsupervised dictionary learning is good for reconstruction, not necessarily effective for classification.

59 Supervised Dictionary Learning The unsupervised dictionary learning is good for reconstruction, not necessarily effective for classification. Training data with image labels {(X i, y i )} N i=1.

60 Supervised Dictionary Learning The unsupervised dictionary learning is good for reconstruction, not necessarily effective for classification. Training data with image labels {(X i, y i )} N i=1. Train the dictionary together with the classifier { N } min D,w i=1 l(y i, f (β i, w)) + γ w 2 2 s.t. β i = pooling(z i ) Z i = arg min A X i DA λ A 1 D(:, k) 2 1, k, where l( ) is a loss function and f (, w) is the linear prediction model. Optimization for w is training the classifier. Optimization for D is a bilevel program.,

61 Face recognition CMU Multi-PIE Database This dataset contains 337 subjects across simultaneous variations in pose, expression, and illumination. We use session 1 as training, and the rest sessions 2-4 for testing. The dataset is challenging due to the large number of subjects, and due to natural variations in subject appearance over time.

62 Face recognition Face recognition error (%) on large-scale Multi-PIE. Rec. Rates Session 2 Session 3 Session 4 LDA NN NS SR U-SC S-SC Improvements 11.1% 26.7% 34.7%

63 Gender Recognition FRGC 2.0 The dataset contains 568 individuals, totally face images under various lighting conditions and backgrounds images from 451 randomly chosen individuals serve as the training set, and 3014 images from the rest 114 persons are modeled as the testing set. Classification Error (%) Algorithms SVM (RBF) CNN U-SC S-SC Improvements Error Rate %

64 Hand Written Digit Recognition MNIST: The dataset consists of 70,000 handwritten digits, of which 60,000 are selected for training and the rest 10,000 for testing. Algorithms Error Rate SVM (RBF) 1.41 L1 sparse coding 2.02 Local coordinate coding 1.90 Deep Belief Network 1.20 CNN 0.82 U-SC 0.98 S-SC 0.84 Improvements 14.3%

65 : Outline 1 2 The learning model The learning algorithm 3 4

66 Formulation Let x be the original signal, Φ be the sampling matrix, and y = Φx be the linear measurements. Compressive sensing recovery is done by z = min α 1, s.t. y = ΦD x α α ˆx =D x z

67 Formulation Let x be the original signal, Φ be the sampling matrix, and y = Φx be the linear measurements. Compressive sensing recovery is done by z = min α 1, s.t. y = ΦD x α α ˆx =D x z D x is important for the recovery quality.

68 Formulation Let x be the original signal, Φ be the sampling matrix, and y = Φx be the linear measurements. Compressive sensing recovery is done by z = min α 1, s.t. y = ΦD x α α ˆx =D x z D x is important for the recovery quality. With the training samples {x i } N i=1, learn D x by directly minimizing the compressive sensing recovery error: 1 min D x N N x i D x z i 2 2 i=1 s.t. y i = Φx i, D y = ΦD x z i = arg min α 1, s.t. y i D y α 2 2 ɛ α

69 CS Results Settings: 10, 000 image patches of are randomly sampled for training and 5, 000 for testing from medical images. Haar Wavelet basis is used as our baseline and initialization. Bernouli random matrix is used as the sampling matrix.

70 CS Results Settings: 10, 000 image patches of are randomly sampled for training and 5, 000 for testing from medical images. Haar Wavelet basis is used as our baseline and initialization. Bernouli random matrix is used as the sampling matrix. 2.6 x 105 Cost PSNR Learned Wavelet Iteration Objective value vs. iteration number for 10% sample rate Sampling Rate Recovery accuracy comparison on the test image patches in PSNR.

71 CS Results Image recovery on the bone image with 20% measurements Ground truth Wavelet(22.8 db) Ours (27.6 db)

72 Learning the meaningful representation is critical for many applications Many sparse coding based applications can be formulated as a bilevel program Bilevel programs are extremely useful in many hierarchical models More applications in computer vision and machine learning? E.g., model selection.

Supervised Translation-Invariant Sparse Coding

Supervised Translation-Invariant Sparse Coding Supervised Translation-Invariant Sparse Coding Jianchao Yang,KaiYu, Thomas Huang Beckman Institute, University of Illinois at Urbana-Champaign NEC Laboratories America, Inc., Cupertino, California {jyang29,

More information

Sparse coding for image classification

Sparse coding for image classification Sparse coding for image classification Columbia University Electrical Engineering: Kun Rong(kr2496@columbia.edu) Yongzhou Xiang(yx2211@columbia.edu) Yin Cui(yc2776@columbia.edu) Outline Background Introduction

More information

Sparse Models in Image Understanding And Computer Vision

Sparse Models in Image Understanding And Computer Vision Sparse Models in Image Understanding And Computer Vision Jayaraman J. Thiagarajan Arizona State University Collaborators Prof. Andreas Spanias Karthikeyan Natesan Ramamurthy Sparsity Sparsity of a vector

More information

Single-Image Super-Resolution Using Multihypothesis Prediction

Single-Image Super-Resolution Using Multihypothesis Prediction Single-Image Super-Resolution Using Multihypothesis Prediction Chen Chen and James E. Fowler Department of Electrical and Computer Engineering, Geosystems Research Institute (GRI) Mississippi State University,

More information

LEARNING SPARSE REPRESENTATION FOR IMAGE SIGNALS ZHAOWEN WANG DISSERTATION

LEARNING SPARSE REPRESENTATION FOR IMAGE SIGNALS ZHAOWEN WANG DISSERTATION c 2014 Zhaowen Wang LEARNING SPARSE REPRESENTATION FOR IMAGE SIGNALS BY ZHAOWEN WANG DISSERTATION Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Electrical

More information

Detecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference

Detecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference Detecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference Minh Dao 1, Xiang Xiang 1, Bulent Ayhan 2, Chiman Kwan 2, Trac D. Tran 1 Johns Hopkins Univeristy, 3400

More information

Extended Dictionary Learning : Convolutional and Multiple Feature Spaces

Extended Dictionary Learning : Convolutional and Multiple Feature Spaces Extended Dictionary Learning : Convolutional and Multiple Feature Spaces Konstantina Fotiadou, Greg Tsagkatakis & Panagiotis Tsakalides kfot@ics.forth.gr, greg@ics.forth.gr, tsakalid@ics.forth.gr ICS-

More information

Image Restoration with Deep Generative Models

Image Restoration with Deep Generative Models Image Restoration with Deep Generative Models Raymond A. Yeh *, Teck-Yian Lim *, Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do Department of Electrical and Computer Engineering, University

More information

A DEEP DICTIONARY MODEL FOR IMAGE SUPER-RESOLUTION. Jun-Jie Huang and Pier Luigi Dragotti

A DEEP DICTIONARY MODEL FOR IMAGE SUPER-RESOLUTION. Jun-Jie Huang and Pier Luigi Dragotti A DEEP DICTIONARY MODEL FOR IMAGE SUPER-RESOLUTION Jun-Jie Huang and Pier Luigi Dragotti Communications and Signal Processing Group CSP), Imperial College London, UK ABSTRACT Inspired by the recent success

More information

Guided Image Super-Resolution: A New Technique for Photogeometric Super-Resolution in Hybrid 3-D Range Imaging

Guided Image Super-Resolution: A New Technique for Photogeometric Super-Resolution in Hybrid 3-D Range Imaging Guided Image Super-Resolution: A New Technique for Photogeometric Super-Resolution in Hybrid 3-D Range Imaging Florin C. Ghesu 1, Thomas Köhler 1,2, Sven Haase 1, Joachim Hornegger 1,2 04.09.2014 1 Pattern

More information

arxiv: v1 [cond-mat.dis-nn] 30 Dec 2018

arxiv: v1 [cond-mat.dis-nn] 30 Dec 2018 A General Deep Learning Framework for Structure and Dynamics Reconstruction from Time Series Data arxiv:1812.11482v1 [cond-mat.dis-nn] 30 Dec 2018 Zhang Zhang, Jing Liu, Shuo Wang, Ruyue Xin, Jiang Zhang

More information

Outline Introduction Problem Formulation Proposed Solution Applications Conclusion. Compressed Sensing. David L Donoho Presented by: Nitesh Shroff

Outline Introduction Problem Formulation Proposed Solution Applications Conclusion. Compressed Sensing. David L Donoho Presented by: Nitesh Shroff Compressed Sensing David L Donoho Presented by: Nitesh Shroff University of Maryland Outline 1 Introduction Compressed Sensing 2 Problem Formulation Sparse Signal Problem Statement 3 Proposed Solution

More information

DEEP LEARNING OF COMPRESSED SENSING OPERATORS WITH STRUCTURAL SIMILARITY (SSIM) LOSS

DEEP LEARNING OF COMPRESSED SENSING OPERATORS WITH STRUCTURAL SIMILARITY (SSIM) LOSS DEEP LEARNING OF COMPRESSED SENSING OPERATORS WITH STRUCTURAL SIMILARITY (SSIM) LOSS ABSTRACT Compressed sensing (CS) is a signal processing framework for efficiently reconstructing a signal from a small

More information

Face Recognition via Sparse Representation

Face Recognition via Sparse Representation Face Recognition via Sparse Representation John Wright, Allen Y. Yang, Arvind, S. Shankar Sastry and Yi Ma IEEE Trans. PAMI, March 2008 Research About Face Face Detection Face Alignment Face Recognition

More information

Facial Expression Classification with Random Filters Feature Extraction

Facial Expression Classification with Random Filters Feature Extraction Facial Expression Classification with Random Filters Feature Extraction Mengye Ren Facial Monkey mren@cs.toronto.edu Zhi Hao Luo It s Me lzh@cs.toronto.edu I. ABSTRACT In our work, we attempted to tackle

More information

Multiresponse Sparse Regression with Application to Multidimensional Scaling

Multiresponse Sparse Regression with Application to Multidimensional Scaling Multiresponse Sparse Regression with Application to Multidimensional Scaling Timo Similä and Jarkko Tikka Helsinki University of Technology, Laboratory of Computer and Information Science P.O. Box 54,

More information

Image Restoration Using DNN

Image Restoration Using DNN Image Restoration Using DNN Hila Levi & Eran Amar Images were taken from: http://people.tuebingen.mpg.de/burger/neural_denoising/ Agenda Domain Expertise vs. End-to-End optimization Image Denoising and

More information

The Benefit of Tree Sparsity in Accelerated MRI

The Benefit of Tree Sparsity in Accelerated MRI The Benefit of Tree Sparsity in Accelerated MRI Chen Chen and Junzhou Huang Department of Computer Science and Engineering, The University of Texas at Arlington, TX, USA 76019 Abstract. The wavelet coefficients

More information

One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models

One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models [Supplemental Materials] 1. Network Architecture b ref b ref +1 We now describe the architecture of the networks

More information

COMP 551 Applied Machine Learning Lecture 16: Deep Learning

COMP 551 Applied Machine Learning Lecture 16: Deep Learning COMP 551 Applied Machine Learning Lecture 16: Deep Learning Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted, all

More information

Learning with infinitely many features

Learning with infinitely many features Learning with infinitely many features R. Flamary, Joint work with A. Rakotomamonjy F. Yger, M. Volpi, M. Dalla Mura, D. Tuia Laboratoire Lagrange, Université de Nice Sophia Antipolis December 2012 Example

More information

Vulnerability of machine learning models to adversarial examples

Vulnerability of machine learning models to adversarial examples Vulnerability of machine learning models to adversarial examples Petra Vidnerová Institute of Computer Science The Czech Academy of Sciences Hora Informaticae 1 Outline Introduction Works on adversarial

More information

Sparsity and image processing

Sparsity and image processing Sparsity and image processing Aurélie Boisbunon INRIA-SAM, AYIN March 6, Why sparsity? Main advantages Dimensionality reduction Fast computation Better interpretability Image processing pattern recognition

More information

Iterative CT Reconstruction Using Curvelet-Based Regularization

Iterative CT Reconstruction Using Curvelet-Based Regularization Iterative CT Reconstruction Using Curvelet-Based Regularization Haibo Wu 1,2, Andreas Maier 1, Joachim Hornegger 1,2 1 Pattern Recognition Lab (LME), Department of Computer Science, 2 Graduate School in

More information

An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation

An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation Hugo Larochelle, Dumitru Erhan, Aaron Courville, James Bergstra, and Yoshua Bengio Université de Montréal 13/06/2007

More information

Machine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart

Machine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart Machine Learning The Breadth of ML Neural Networks & Deep Learning Marc Toussaint University of Stuttgart Duy Nguyen-Tuong Bosch Center for Artificial Intelligence Summer 2017 Neural Networks Consider

More information

arxiv: v1 [cs.cv] 9 Sep 2013

arxiv: v1 [cs.cv] 9 Sep 2013 Learning Transformations for Clustering and Classification arxiv:139.274v1 [cs.cv] 9 Sep 213 Qiang Qiu Department of Electrical and Computer Engineering Duke University Durham, NC 2778, USA Guillermo Sapiro

More information

A fast algorithm for sparse reconstruction based on shrinkage, subspace optimization and continuation [Wen,Yin,Goldfarb,Zhang 2009]

A fast algorithm for sparse reconstruction based on shrinkage, subspace optimization and continuation [Wen,Yin,Goldfarb,Zhang 2009] A fast algorithm for sparse reconstruction based on shrinkage, subspace optimization and continuation [Wen,Yin,Goldfarb,Zhang 2009] Yongjia Song University of Wisconsin-Madison April 22, 2010 Yongjia Song

More information

Generalized Tree-Based Wavelet Transform and Applications to Patch-Based Image Processing

Generalized Tree-Based Wavelet Transform and Applications to Patch-Based Image Processing Generalized Tree-Based Wavelet Transform and * Michael Elad The Computer Science Department The Technion Israel Institute of technology Haifa 32000, Israel *Joint work with A Seminar in the Hebrew University

More information

Lecture 17 Sparse Convex Optimization

Lecture 17 Sparse Convex Optimization Lecture 17 Sparse Convex Optimization Compressed sensing A short introduction to Compressed Sensing An imaging perspective 10 Mega Pixels Scene Image compression Picture Why do we compress images? Introduction

More information

Single Image Super Resolution of Textures via CNNs. Andrew Palmer

Single Image Super Resolution of Textures via CNNs. Andrew Palmer Single Image Super Resolution of Textures via CNNs Andrew Palmer What is Super Resolution (SR)? Simple: Obtain one or more high-resolution images from one or more low-resolution ones Many, many applications

More information

Neural Networks and Deep Learning

Neural Networks and Deep Learning Neural Networks and Deep Learning Example Learning Problem Example Learning Problem Celebrity Faces in the Wild Machine Learning Pipeline Raw data Feature extract. Feature computation Inference: prediction,

More information

Stacked Denoising Autoencoders for Face Pose Normalization

Stacked Denoising Autoencoders for Face Pose Normalization Stacked Denoising Autoencoders for Face Pose Normalization Yoonseop Kang 1, Kang-Tae Lee 2,JihyunEun 2, Sung Eun Park 2 and Seungjin Choi 1 1 Department of Computer Science and Engineering Pohang University

More information

Tutorial Deep Learning : Unsupervised Feature Learning

Tutorial Deep Learning : Unsupervised Feature Learning Tutorial Deep Learning : Unsupervised Feature Learning Joana Frontera-Pons 4th September 2017 - Workshop Dictionary Learning on Manifolds OUTLINE Introduction Representation Learning TensorFlow Examples

More information

Non-Differentiable Image Manifolds

Non-Differentiable Image Manifolds The Multiscale Structure of Non-Differentiable Image Manifolds Michael Wakin Electrical l Engineering i Colorado School of Mines Joint work with Richard Baraniuk, Hyeokho Choi, David Donoho Models for

More information

GEOMETRIC MANIFOLD APPROXIMATION USING LOCALLY LINEAR APPROXIMATIONS

GEOMETRIC MANIFOLD APPROXIMATION USING LOCALLY LINEAR APPROXIMATIONS GEOMETRIC MANIFOLD APPROXIMATION USING LOCALLY LINEAR APPROXIMATIONS BY TALAL AHMED A thesis submitted to the Graduate School New Brunswick Rutgers, The State University of New Jersey in partial fulfillment

More information

Backpropagation + Deep Learning

Backpropagation + Deep Learning 10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Backpropagation + Deep Learning Matt Gormley Lecture 13 Mar 1, 2018 1 Reminders

More information

ELEG Compressive Sensing and Sparse Signal Representations

ELEG Compressive Sensing and Sparse Signal Representations ELEG 867 - Compressive Sensing and Sparse Signal Representations Gonzalo R. Arce Depart. of Electrical and Computer Engineering University of Delaware Fall 211 Compressive Sensing G. Arce Fall, 211 1 /

More information

Dimensionality reduction of MALDI Imaging datasets using non-linear redundant wavelet transform-based representations

Dimensionality reduction of MALDI Imaging datasets using non-linear redundant wavelet transform-based representations Dimensionality reduction of MALDI Imaging datasets using non-linear redundant wavelet transform-based representations Luis Mancera 1, Lyna Sellami 2, Jamie Cunliffe 2, Luis González 1, Omar Belgacem 2

More information

Deep Learning of Compressed Sensing Operators with Structural Similarity Loss

Deep Learning of Compressed Sensing Operators with Structural Similarity Loss Deep Learning of Compressed Sensing Operators with Structural Similarity Loss Y. Zur and A. Adler Abstract Compressed sensing CS is a signal processing framework for efficiently reconstructing a signal

More information

A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network. Zhe Li, Shu Li, Jianmin Wang and Hongyang Wang

A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network. Zhe Li, Shu Li, Jianmin Wang and Hongyang Wang 5th International Conference on Measurement, Instrumentation and Automation (ICMIA 2016) A Novel Multi-Frame Color Images Super-Resolution Framewor based on Deep Convolutional Neural Networ Zhe Li, Shu

More information

Lecture 19: November 5

Lecture 19: November 5 0-725/36-725: Convex Optimization Fall 205 Lecturer: Ryan Tibshirani Lecture 9: November 5 Scribes: Hyun Ah Song Note: LaTeX template courtesy of UC Berkeley EECS dept. Disclaimer: These notes have not

More information

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images Marc Aurelio Ranzato Yann LeCun Courant Institute of Mathematical Sciences New York University - New York, NY 10003 Abstract

More information

Optimization. Industrial AI Lab.

Optimization. Industrial AI Lab. Optimization Industrial AI Lab. Optimization An important tool in 1) Engineering problem solving and 2) Decision science People optimize Nature optimizes 2 Optimization People optimize (source: http://nautil.us/blog/to-save-drowning-people-ask-yourself-what-would-light-do)

More information

Perceptron: This is convolution!

Perceptron: This is convolution! Perceptron: This is convolution! v v v Shared weights v Filter = local perceptron. Also called kernel. By pooling responses at different locations, we gain robustness to the exact spatial location of image

More information

Image Restoration: From Sparse and Low-rank Priors to Deep Priors

Image Restoration: From Sparse and Low-rank Priors to Deep Priors Image Restoration: From Sparse and Low-rank Priors to Deep Priors Lei Zhang 1, Wangmeng Zuo 2 1 Dept. of computing, The Hong Kong Polytechnic University, 2 School of Computer Science and Technology, Harbin

More information

Deep Learning. Vladimir Golkov Technical University of Munich Computer Vision Group

Deep Learning. Vladimir Golkov Technical University of Munich Computer Vision Group Deep Learning Vladimir Golkov Technical University of Munich Computer Vision Group 1D Input, 1D Output target input 2 2D Input, 1D Output: Data Distribution Complexity Imagine many dimensions (data occupies

More information

Robust Face Recognition via Sparse Representation Authors: John Wright, Allen Y. Yang, Arvind Ganesh, S. Shankar Sastry, and Yi Ma

Robust Face Recognition via Sparse Representation Authors: John Wright, Allen Y. Yang, Arvind Ganesh, S. Shankar Sastry, and Yi Ma Robust Face Recognition via Sparse Representation Authors: John Wright, Allen Y. Yang, Arvind Ganesh, S. Shankar Sastry, and Yi Ma Presented by Hu Han Jan. 30 2014 For CSE 902 by Prof. Anil K. Jain: Selected

More information

Robust Face Recognition via Sparse Representation

Robust Face Recognition via Sparse Representation Robust Face Recognition via Sparse Representation Panqu Wang Department of Electrical and Computer Engineering University of California, San Diego La Jolla, CA 92092 pawang@ucsd.edu Can Xu Department of

More information

Learning Algorithms for Medical Image Analysis. Matteo Santoro slipguru

Learning Algorithms for Medical Image Analysis. Matteo Santoro slipguru Learning Algorithms for Medical Image Analysis Matteo Santoro slipguru santoro@disi.unige.it June 8, 2010 Outline 1. learning-based strategies for quantitative image analysis 2. automatic annotation of

More information

Learning Low-rank Transformations: Algorithms and Applications. Qiang Qiu Guillermo Sapiro

Learning Low-rank Transformations: Algorithms and Applications. Qiang Qiu Guillermo Sapiro Learning Low-rank Transformations: Algorithms and Applications Qiang Qiu Guillermo Sapiro Motivation Outline Low-rank transform - algorithms and theories Applications Subspace clustering Classification

More information

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images Marc Aurelio Ranzato Yann LeCun Courant Institute of Mathematical Sciences New York University - New York, NY 10003 Abstract

More information

Efficient MR Image Reconstruction for Compressed MR Imaging

Efficient MR Image Reconstruction for Compressed MR Imaging Efficient MR Image Reconstruction for Compressed MR Imaging Junzhou Huang, Shaoting Zhang, and Dimitris Metaxas Division of Computer and Information Sciences, Rutgers University, NJ, USA 08854 Abstract.

More information

Convex and Distributed Optimization. Thomas Ropars

Convex and Distributed Optimization. Thomas Ropars >>> Presentation of this master2 course Convex and Distributed Optimization Franck Iutzeler Jérôme Malick Thomas Ropars Dmitry Grishchenko from LJK, the applied maths and computer science laboratory and

More information

Akarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction

Akarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction Akarsh Pokkunuru EECS Department 03-16-2017 Contractive Auto-Encoders: Explicit Invariance During Feature Extraction 1 AGENDA Introduction to Auto-encoders Types of Auto-encoders Analysis of different

More information

Example-Based Image Super-Resolution Techniques

Example-Based Image Super-Resolution Techniques Example-Based Image Super-Resolution Techniques Mark Sabini msabini & Gili Rusak gili December 17, 2016 1 Introduction With the current surge in popularity of imagebased applications, improving content

More information

Extracting and Composing Robust Features with Denoising Autoencoders

Extracting and Composing Robust Features with Denoising Autoencoders Presenter: Alexander Truong March 16, 2017 Extracting and Composing Robust Features with Denoising Autoencoders Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol 1 Outline Introduction

More information

Recent Developments in Model-based Derivative-free Optimization

Recent Developments in Model-based Derivative-free Optimization Recent Developments in Model-based Derivative-free Optimization Seppo Pulkkinen April 23, 2010 Introduction Problem definition The problem we are considering is a nonlinear optimization problem with constraints:

More information

Complex Prediction Problems

Complex Prediction Problems Problems A novel approach to multiple Structured Output Prediction Max-Planck Institute ECML HLIE08 Information Extraction Extract structured information from unstructured data Typical subtasks Named Entity

More information

A primal-dual framework for mixtures of regularizers

A primal-dual framework for mixtures of regularizers A primal-dual framework for mixtures of regularizers Baran Gözcü baran.goezcue@epfl.ch Laboratory for Information and Inference Systems (LIONS) École Polytechnique Fédérale de Lausanne (EPFL) Switzerland

More information

Learning Feature Hierarchies for Object Recognition

Learning Feature Hierarchies for Object Recognition Learning Feature Hierarchies for Object Recognition Koray Kavukcuoglu Computer Science Department Courant Institute of Mathematical Sciences New York University Marc Aurelio Ranzato, Kevin Jarrett, Pierre

More information

Deep Generative Models Variational Autoencoders

Deep Generative Models Variational Autoencoders Deep Generative Models Variational Autoencoders Sudeshna Sarkar 5 April 2017 Generative Nets Generative models that represent probability distributions over multiple variables in some way. Directed Generative

More information

Learning based face hallucination techniques: A survey

Learning based face hallucination techniques: A survey Vol. 3 (2014-15) pp. 37-45. : A survey Premitha Premnath K Department of Computer Science & Engineering Vidya Academy of Science & Technology Thrissur - 680501, Kerala, India (email: premithakpnath@gmail.com)

More information

When Sparsity Meets Low-Rankness: Transform Learning With Non-Local Low-Rank Constraint For Image Restoration

When Sparsity Meets Low-Rankness: Transform Learning With Non-Local Low-Rank Constraint For Image Restoration When Sparsity Meets Low-Rankness: Transform Learning With Non-Local Low-Rank Constraint For Image Restoration Bihan Wen, Yanjun Li and Yoram Bresler Department of Electrical and Computer Engineering Coordinated

More information

Face Recognition A Deep Learning Approach

Face Recognition A Deep Learning Approach Face Recognition A Deep Learning Approach Lihi Shiloh Tal Perl Deep Learning Seminar 2 Outline What about Cat recognition? Classical face recognition Modern face recognition DeepFace FaceNet Comparison

More information

arxiv: v2 [cs.lg] 6 Jun 2015

arxiv: v2 [cs.lg] 6 Jun 2015 HOPE (Zhang and Jiang) 1 Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural Networks Shiliang Zhang and Hui Jiang arxiv:1502.00702v2 [cs.lg 6 Jun 2015 National

More information

Markov Random Fields and Gibbs Sampling for Image Denoising

Markov Random Fields and Gibbs Sampling for Image Denoising Markov Random Fields and Gibbs Sampling for Image Denoising Chang Yue Electrical Engineering Stanford University changyue@stanfoed.edu Abstract This project applies Gibbs Sampling based on different Markov

More information

Compressive Sensing for Multimedia. Communications in Wireless Sensor Networks

Compressive Sensing for Multimedia. Communications in Wireless Sensor Networks Compressive Sensing for Multimedia 1 Communications in Wireless Sensor Networks Wael Barakat & Rabih Saliba MDDSP Project Final Report Prof. Brian L. Evans May 9, 2008 Abstract Compressive Sensing is an

More information

Unsupervised Learning of Spatiotemporally Coherent Metrics

Unsupervised Learning of Spatiotemporally Coherent Metrics Unsupervised Learning of Spatiotemporally Coherent Metrics Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun arxiv 2015. Presented by Jackie Chu Contributions Insight between slow feature

More information

Relation among images: Modelling, optimization and applications

Relation among images: Modelling, optimization and applications Purdue University Purdue e-pubs Open Access Dissertations Theses and Dissertations Fall 2014 Relation among images: Modelling, optimization and applications Bin Shen Purdue University Follow this and additional

More information

Edge-Based Blur Kernel Estimation Using Sparse Representation and Self-Similarity

Edge-Based Blur Kernel Estimation Using Sparse Representation and Self-Similarity Noname manuscript No. (will be inserted by the editor) Edge-Based Blur Kernel Estimation Using Sparse Representation and Self-Similarity Jing Yu Zhenchun Chang Chuangbai Xiao Received: date / Accepted:

More information

Machine Learning / Jan 27, 2010

Machine Learning / Jan 27, 2010 Revisiting Logistic Regression & Naïve Bayes Aarti Singh Machine Learning 10-701/15-781 Jan 27, 2010 Generative and Discriminative Classifiers Training classifiers involves learning a mapping f: X -> Y,

More information

Some Blind Deconvolution Techniques in Image Processing

Some Blind Deconvolution Techniques in Image Processing Some Blind Deconvolution Techniques in Image Processing Tony Chan Math Dept., UCLA Joint work with Frederick Park and Andy M. Yip IPAM Workshop on Mathematical Challenges in Astronomical Imaging July 26-30,

More information

Image Super-Resolution via Sparse Representation

Image Super-Resolution via Sparse Representation Image Super-Resolution via Sparse Representation Jianchao Yang, John Wright, Thomas Huang and Yi Ma accepted by IEEE Trans. on Image Processing 2010 Presented by known 2010/4/20 1 Super-Resolution Techniques

More information

Fast Learning-Based Single Image Super-Resolution

Fast Learning-Based Single Image Super-Resolution 1 Fast Learning-Based Single Image Super-Resolution Neeraj Kumar and Amit Sethi Abstract We present a learning-based single image superresolution (SISR) method to obtain a high resolution (HR) image from

More information

Learning Convolutional Feature Hierarchies for Visual Recognition

Learning Convolutional Feature Hierarchies for Visual Recognition Learning Convolutional Feature Hierarchies for Visual Recognition Koray Kavukcuoglu, Pierre Sermanet, Y-Lan Boureau, Karol Gregor, Michael Mathieu, Yann LeCun Computer Science Department Courant Institute

More information

3194 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 7, JULY 2016

3194 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 7, JULY 2016 3194 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 7, JULY 2016 Robust Single Image Super-Resolution via Deep Networks With Sparse Prior Ding Liu, Student Member, IEEE, Zhaowen Wang, Member, IEEE,

More information

arxiv: v1 [cs.lg] 20 Dec 2013

arxiv: v1 [cs.lg] 20 Dec 2013 Unsupervised Feature Learning by Deep Sparse Coding Yunlong He Koray Kavukcuoglu Yun Wang Arthur Szlam Yanjun Qi arxiv:1312.5783v1 [cs.lg] 20 Dec 2013 Abstract In this paper, we propose a new unsupervised

More information

CSC 411 Lecture 18: Matrix Factorizations

CSC 411 Lecture 18: Matrix Factorizations CSC 411 Lecture 18: Matrix Factorizations Roger Grosse, Amir-massoud Farahmand, and Juan Carrasquilla University of Toronto UofT CSC 411: 18-Matrix Factorizations 1 / 27 Overview Recall PCA: project data

More information

The exam is closed book, closed notes except your one-page (two-sided) cheat sheet.

The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. CS 189 Spring 2015 Introduction to Machine Learning Final You have 2 hours 50 minutes for the exam. The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. No calculators or

More information

Learning Visual Semantics: Models, Massive Computation, and Innovative Applications

Learning Visual Semantics: Models, Massive Computation, and Innovative Applications Learning Visual Semantics: Models, Massive Computation, and Innovative Applications Part II: Visual Features and Representations Liangliang Cao, IBM Watson Research Center Evolvement of Visual Features

More information

A Taxonomy of Semi-Supervised Learning Algorithms

A Taxonomy of Semi-Supervised Learning Algorithms A Taxonomy of Semi-Supervised Learning Algorithms Olivier Chapelle Max Planck Institute for Biological Cybernetics December 2005 Outline 1 Introduction 2 Generative models 3 Low density separation 4 Graph

More information

Sparsity Based Regularization

Sparsity Based Regularization 9.520: Statistical Learning Theory and Applications March 8th, 200 Sparsity Based Regularization Lecturer: Lorenzo Rosasco Scribe: Ioannis Gkioulekas Introduction In previous lectures, we saw how regularization

More information

Section 5 Convex Optimisation 1. W. Dai (IC) EE4.66 Data Proc. Convex Optimisation page 5-1

Section 5 Convex Optimisation 1. W. Dai (IC) EE4.66 Data Proc. Convex Optimisation page 5-1 Section 5 Convex Optimisation 1 W. Dai (IC) EE4.66 Data Proc. Convex Optimisation 1 2018 page 5-1 Convex Combination Denition 5.1 A convex combination is a linear combination of points where all coecients

More information

DS Machine Learning and Data Mining I. Alina Oprea Associate Professor, CCIS Northeastern University

DS Machine Learning and Data Mining I. Alina Oprea Associate Professor, CCIS Northeastern University DS 4400 Machine Learning and Data Mining I Alina Oprea Associate Professor, CCIS Northeastern University September 20 2018 Review Solution for multiple linear regression can be computed in closed form

More information

C. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun

C. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun Efficient Learning of Sparse Overcomplete Representations with an Energy-Based Model Marc'Aurelio Ranzato C. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun CIAR Summer School Toronto 2006 Why Extracting

More information

Energy Based Models, Restricted Boltzmann Machines and Deep Networks. Jesse Eickholt

Energy Based Models, Restricted Boltzmann Machines and Deep Networks. Jesse Eickholt Energy Based Models, Restricted Boltzmann Machines and Deep Networks Jesse Eickholt ???? Who s heard of Energy Based Models (EBMs) Restricted Boltzmann Machines (RBMs) Deep Belief Networks Auto-encoders

More information

LEARNING A SPARSE DICTIONARY OF VIDEO STRUCTURE FOR ACTIVITY MODELING. Nandita M. Nayak, Amit K. Roy-Chowdhury. University of California, Riverside

LEARNING A SPARSE DICTIONARY OF VIDEO STRUCTURE FOR ACTIVITY MODELING. Nandita M. Nayak, Amit K. Roy-Chowdhury. University of California, Riverside LEARNING A SPARSE DICTIONARY OF VIDEO STRUCTURE FOR ACTIVITY MODELING Nandita M. Nayak, Amit K. Roy-Chowdhury University of California, Riverside ABSTRACT We present an approach which incorporates spatiotemporal

More information

ECG782: Multidimensional Digital Signal Processing

ECG782: Multidimensional Digital Signal Processing ECG782: Multidimensional Digital Signal Processing Object Recognition http://www.ee.unlv.edu/~b1morris/ecg782/ 2 Outline Knowledge Representation Statistical Pattern Recognition Neural Networks Boosting

More information

CS294-1 Assignment 2 Report

CS294-1 Assignment 2 Report CS294-1 Assignment 2 Report Keling Chen and Huasha Zhao February 24, 2012 1 Introduction The goal of this homework is to predict a users numeric rating for a book from the text of the user s review. The

More information

ICA mixture models for image processing

ICA mixture models for image processing I999 6th Joint Sy~nposiurn orz Neural Computation Proceedings ICA mixture models for image processing Te-Won Lee Michael S. Lewicki The Salk Institute, CNL Carnegie Mellon University, CS & CNBC 10010 N.

More information

Adaptive Reconstruction Methods for Low-Dose Computed Tomography

Adaptive Reconstruction Methods for Low-Dose Computed Tomography Adaptive Reconstruction Methods for Low-Dose Computed Tomography Joseph Shtok Ph.D. supervisors: Prof. Michael Elad, Dr. Michael Zibulevsky. Technion IIT, Israel, 011 Ph.D. Talk, Apr. 01 Contents of this

More information

Introduction to Machine Learning. Xiaojin Zhu

Introduction to Machine Learning. Xiaojin Zhu Introduction to Machine Learning Xiaojin Zhu jerryzhu@cs.wisc.edu Read Chapter 1 of this book: Xiaojin Zhu and Andrew B. Goldberg. Introduction to Semi- Supervised Learning. http://www.morganclaypool.com/doi/abs/10.2200/s00196ed1v01y200906aim006

More information

A Patch Prior for Dense 3D Reconstruction in Man-Made Environments

A Patch Prior for Dense 3D Reconstruction in Man-Made Environments A Patch Prior for Dense 3D Reconstruction in Man-Made Environments Christian Häne 1, Christopher Zach 2, Bernhard Zeisl 1, Marc Pollefeys 1 1 ETH Zürich 2 MSR Cambridge October 14, 2012 A Patch Prior for

More information

Modern Signal Processing and Sparse Coding

Modern Signal Processing and Sparse Coding Modern Signal Processing and Sparse Coding School of Electrical and Computer Engineering Georgia Institute of Technology March 22 2011 Reason D etre Modern signal processing Signals without cosines? Sparse

More information

CAP 6412 Advanced Computer Vision

CAP 6412 Advanced Computer Vision CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 21st, 2016 Today Administrivia Free parameters in an approach, model, or algorithm? Egocentric videos by Aisha

More information

Imaging of flow in porous media - from optimal transport to prediction

Imaging of flow in porous media - from optimal transport to prediction Imaging of flow in porous media - from optimal transport to prediction Eldad Haber Dept of EOS and Mathematics, UBC October 15, 2013 With Rowan Lars Jenn Cocket Ruthotto Fohring Outline Prediction is very

More information

Inverse Problems and Machine Learning

Inverse Problems and Machine Learning Inverse Problems and Machine Learning Julian Wörmann Research Group for Geometric Optimization and Machine Learning (GOL) 1 What are inverse problems? 2 Inverse Problems cause/ excitation 3 Inverse Problems

More information

IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. XX, NO. XX, XXXX 1

IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. XX, NO. XX, XXXX 1 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. XX, NO. XX, XXXX 1 Semi-Supervised Sparse Representation Based Classification for Face Recognition with Insufficient Labeled Samples Yuan Gao, Jiayi Ma, and

More information

An efficient face recognition algorithm based on multi-kernel regularization learning

An efficient face recognition algorithm based on multi-kernel regularization learning Acta Technica 61, No. 4A/2016, 75 84 c 2017 Institute of Thermomechanics CAS, v.v.i. An efficient face recognition algorithm based on multi-kernel regularization learning Bi Rongrong 1 Abstract. A novel

More information