Sorry, you need to enable JavaScript to visit this website.

Information-theoretic learning (MLR-INFO)

CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING


A simple and scalable denoising algorithm is proposed that can be applied to a wide range of source and noise models. At the core of the proposed CUDE algorithm is symbol-by-symbol universal denoising used by the celebrated DUDE algorithm, whereby the optimal estimate of the source from an unknown distribution is computed by inverting the empirical distribution of the noisy observation sequence by a deep neural network, which naturally and implicitly aggregates multiple contexts of similar characteristics and estimates the conditional distribution more accurately.

Paper Details

Authors:
Jongha Jon Ryu, Young-Han Kim
Submitted On:
8 October 2018 - 3:38am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip2018-poster-cude.pdf

(6 downloads)

Subscribe

[1] Jongha Jon Ryu, Young-Han Kim, "CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3616. Accessed: Oct. 19, 2018.
@article{3616-18,
url = {http://sigport.org/3616},
author = {Jongha Jon Ryu; Young-Han Kim },
publisher = {IEEE SigPort},
title = {CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING},
year = {2018} }
TY - EJOUR
T1 - CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING
AU - Jongha Jon Ryu; Young-Han Kim
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3616
ER -
Jongha Jon Ryu, Young-Han Kim. (2018). CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING. IEEE SigPort. http://sigport.org/3616
Jongha Jon Ryu, Young-Han Kim, 2018. CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING. Available at: http://sigport.org/3616.
Jongha Jon Ryu, Young-Han Kim. (2018). "CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING." Web.
1. Jongha Jon Ryu, Young-Han Kim. CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3616

ON THE GEOMETRY OF MIXTURES OF PRESCRIBED DISTRIBUTIONS

Paper Details

Authors:
Submitted On:
23 April 2018 - 12:06am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

GeometryMixtures-Poster-ICASSP2018.pdf

(69 downloads)

Subscribe

[1] , "ON THE GEOMETRY OF MIXTURES OF PRESCRIBED DISTRIBUTIONS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3143. Accessed: Oct. 19, 2018.
@article{3143-18,
url = {http://sigport.org/3143},
author = { },
publisher = {IEEE SigPort},
title = {ON THE GEOMETRY OF MIXTURES OF PRESCRIBED DISTRIBUTIONS},
year = {2018} }
TY - EJOUR
T1 - ON THE GEOMETRY OF MIXTURES OF PRESCRIBED DISTRIBUTIONS
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3143
ER -
. (2018). ON THE GEOMETRY OF MIXTURES OF PRESCRIBED DISTRIBUTIONS. IEEE SigPort. http://sigport.org/3143
, 2018. ON THE GEOMETRY OF MIXTURES OF PRESCRIBED DISTRIBUTIONS. Available at: http://sigport.org/3143.
. (2018). "ON THE GEOMETRY OF MIXTURES OF PRESCRIBED DISTRIBUTIONS." Web.
1. . ON THE GEOMETRY OF MIXTURES OF PRESCRIBED DISTRIBUTIONS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3143

RATE-OPTIMAL META LEARNING OF CLASSIFICATION ERROR


Meta learning of optimal classifier error rates allows an experimenter to empirically estimate the intrinsic ability of any estimator to discriminate between two populations, circumventing the difficult problem of estimating the optimal Bayes classifier. To this end we propose a weighted nearest neighbor (WNN) graph estimator for a tight bound on the Bayes classification error; the Henze-Penrose (HP) divergence. Similar to recently proposed HP estimators [berisha2016], the proposed estimator is non-parametric and does not require density estimation.

Paper Details

Authors:
Morteza Noshad, Alfred Hero
Submitted On:
16 April 2018 - 12:28am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

icassp-poster-v3.pdf

(67 downloads)

Subscribe

[1] Morteza Noshad, Alfred Hero, "RATE-OPTIMAL META LEARNING OF CLASSIFICATION ERROR", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2907. Accessed: Oct. 19, 2018.
@article{2907-18,
url = {http://sigport.org/2907},
author = {Morteza Noshad; Alfred Hero },
publisher = {IEEE SigPort},
title = {RATE-OPTIMAL META LEARNING OF CLASSIFICATION ERROR},
year = {2018} }
TY - EJOUR
T1 - RATE-OPTIMAL META LEARNING OF CLASSIFICATION ERROR
AU - Morteza Noshad; Alfred Hero
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2907
ER -
Morteza Noshad, Alfred Hero. (2018). RATE-OPTIMAL META LEARNING OF CLASSIFICATION ERROR. IEEE SigPort. http://sigport.org/2907
Morteza Noshad, Alfred Hero, 2018. RATE-OPTIMAL META LEARNING OF CLASSIFICATION ERROR. Available at: http://sigport.org/2907.
Morteza Noshad, Alfred Hero. (2018). "RATE-OPTIMAL META LEARNING OF CLASSIFICATION ERROR." Web.
1. Morteza Noshad, Alfred Hero. RATE-OPTIMAL META LEARNING OF CLASSIFICATION ERROR [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2907

Rate-optimal Meta Learning of Classification Error


Meta learning of optimal classifier error rates allows an experimenter to empirically estimate the intrinsic ability of any estimator to discriminate between two populations, circumventing the difficult problem of estimating the optimal Bayes classifier. To this end we propose a weighted nearest neighbor (WNN) graph estimator for a tight bound on the Bayes classification error; the Henze-Penrose (HP) divergence. Similar to recently proposed HP estimators [berisha2016], the proposed estimator is non-parametric and does not require density estimation.

Paper Details

Authors:
Morteza Noshad, Alfred Hero
Submitted On:
16 April 2018 - 12:28am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp-poster-v3.pdf

(69 downloads)

Subscribe

[1] Morteza Noshad, Alfred Hero, "Rate-optimal Meta Learning of Classification Error", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2906. Accessed: Oct. 19, 2018.
@article{2906-18,
url = {http://sigport.org/2906},
author = {Morteza Noshad; Alfred Hero },
publisher = {IEEE SigPort},
title = {Rate-optimal Meta Learning of Classification Error},
year = {2018} }
TY - EJOUR
T1 - Rate-optimal Meta Learning of Classification Error
AU - Morteza Noshad; Alfred Hero
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2906
ER -
Morteza Noshad, Alfred Hero. (2018). Rate-optimal Meta Learning of Classification Error. IEEE SigPort. http://sigport.org/2906
Morteza Noshad, Alfred Hero, 2018. Rate-optimal Meta Learning of Classification Error. Available at: http://sigport.org/2906.
Morteza Noshad, Alfred Hero. (2018). "Rate-optimal Meta Learning of Classification Error." Web.
1. Morteza Noshad, Alfred Hero. Rate-optimal Meta Learning of Classification Error [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2906

A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising


A learning-based framework for representation of domain-specific images is proposed where joint compression and denoising can be done using a VQ-based multi-layer network. While it learns to compress the images from a training set, the compression performance is very well generalized on images from a test set. Moreover, when fed with noisy versions of the test set, since it has priors from clean images, the network also efficiently denoises the test images during the reconstruction.

Paper Details

Authors:
Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov
Submitted On:
15 September 2017 - 10:56am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Multi-layer image representation

(135 downloads)

Subscribe

[1] Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov, "A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2138. Accessed: Oct. 19, 2018.
@article{2138-17,
url = {http://sigport.org/2138},
author = {Sohrab Ferdowsi; Slava Voloshynovskiy; Dimche Kostadinov },
publisher = {IEEE SigPort},
title = {A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising},
year = {2017} }
TY - EJOUR
T1 - A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising
AU - Sohrab Ferdowsi; Slava Voloshynovskiy; Dimche Kostadinov
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2138
ER -
Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov. (2017). A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising. IEEE SigPort. http://sigport.org/2138
Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov, 2017. A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising. Available at: http://sigport.org/2138.
Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov. (2017). "A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising." Web.
1. Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov. A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2138

AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING


Screen content has different characteristics compared with natural content captured by cameras. To achieve more efficient compression, some new coding tools have been developed in the High Efficiency Video Coding (HEVC) Screen Content Coding (SCC) Extension, which also increase the computational complexity of encoder. In this paper, complexity analysis are first conducted to explore the distribution of complexities.

Paper Details

Authors:
Liquan Shen, Ping An
Submitted On:
15 September 2017 - 5:05am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017 poster of paper #1561

(163 downloads)

Subscribe

[1] Liquan Shen, Ping An, "AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2114. Accessed: Oct. 19, 2018.
@article{2114-17,
url = {http://sigport.org/2114},
author = {Liquan Shen; Ping An },
publisher = {IEEE SigPort},
title = {AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING},
year = {2017} }
TY - EJOUR
T1 - AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING
AU - Liquan Shen; Ping An
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2114
ER -
Liquan Shen, Ping An. (2017). AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING. IEEE SigPort. http://sigport.org/2114
Liquan Shen, Ping An, 2017. AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING. Available at: http://sigport.org/2114.
Liquan Shen, Ping An. (2017). "AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING." Web.
1. Liquan Shen, Ping An. AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2114

AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING


Screen content has different characteristics compared with natural content captured by cameras. To achieve more efficient compression, some new coding tools have been developed in the High Efficiency Video Coding (HEVC) Screen Content Coding (SCC) Extension, which also increase the computational complexity of encoder. In this paper, complexity analysis are first conducted to explore the distribution of complexities.

Paper Details

Authors:
Liquan Shen, Ping An
Submitted On:
15 September 2017 - 5:05am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP 2017 paper ID: 1561

(130 downloads)

Subscribe

[1] Liquan Shen, Ping An, "AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2112. Accessed: Oct. 19, 2018.
@article{2112-17,
url = {http://sigport.org/2112},
author = {Liquan Shen; Ping An },
publisher = {IEEE SigPort},
title = {AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING},
year = {2017} }
TY - EJOUR
T1 - AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING
AU - Liquan Shen; Ping An
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2112
ER -
Liquan Shen, Ping An. (2017). AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING. IEEE SigPort. http://sigport.org/2112
Liquan Shen, Ping An, 2017. AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING. Available at: http://sigport.org/2112.
Liquan Shen, Ping An. (2017). "AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING." Web.
1. Liquan Shen, Ping An. AN EFFICIENT INTRA CODING ALGORITHM BASED ON STATISTICAL LEARNING FOR SCREEN CONTENT CODING [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2112

INFORMATION POINT SET REGISTRATION FOR SHAPE RECOGNITION


This is an overview poster of the paper INFORMATION POINT SET REGISTRATION FOR SHAPE RECOGNITION.

Paper Details

Authors:
Zheng Cao, Jose C. Principe, Bing Ouyang
Submitted On:
12 March 2016 - 1:40pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

zheng_icassp16_2.pdf

(352 downloads)

Subscribe

[1] Zheng Cao, Jose C. Principe, Bing Ouyang, "INFORMATION POINT SET REGISTRATION FOR SHAPE RECOGNITION", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/646. Accessed: Oct. 19, 2018.
@article{646-16,
url = {http://sigport.org/646},
author = {Zheng Cao; Jose C. Principe; Bing Ouyang },
publisher = {IEEE SigPort},
title = {INFORMATION POINT SET REGISTRATION FOR SHAPE RECOGNITION},
year = {2016} }
TY - EJOUR
T1 - INFORMATION POINT SET REGISTRATION FOR SHAPE RECOGNITION
AU - Zheng Cao; Jose C. Principe; Bing Ouyang
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/646
ER -
Zheng Cao, Jose C. Principe, Bing Ouyang. (2016). INFORMATION POINT SET REGISTRATION FOR SHAPE RECOGNITION. IEEE SigPort. http://sigport.org/646
Zheng Cao, Jose C. Principe, Bing Ouyang, 2016. INFORMATION POINT SET REGISTRATION FOR SHAPE RECOGNITION. Available at: http://sigport.org/646.
Zheng Cao, Jose C. Principe, Bing Ouyang. (2016). "INFORMATION POINT SET REGISTRATION FOR SHAPE RECOGNITION." Web.
1. Zheng Cao, Jose C. Principe, Bing Ouyang. INFORMATION POINT SET REGISTRATION FOR SHAPE RECOGNITION [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/646