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

Machine Learning for Signal Processing

Sparse Modeling


Sparse Modeling in Image Processing and Deep LearningSparse approximation is a well-established theory, with a profound impact on the fields of signal and image processing. In this talk we start by presenting this model and its features, and then turn to describe two special cases of it – the convolutional sparse coding (CSC) and its multi-layered version (ML-CSC).  Amazingly, as we will carefully show, ML-CSC provides a solid theoretical foundation to … deep-learning.

Paper Details

Authors:
Michael Elad
Submitted On:
22 December 2017 - 1:26pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP_KeyNote_Talk_small size.pdf

(305 downloads)

Subscribe

[1] Michael Elad, "Sparse Modeling ", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2260. Accessed: Jan. 19, 2019.
@article{2260-17,
url = {http://sigport.org/2260},
author = {Michael Elad },
publisher = {IEEE SigPort},
title = {Sparse Modeling },
year = {2017} }
TY - EJOUR
T1 - Sparse Modeling
AU - Michael Elad
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2260
ER -
Michael Elad. (2017). Sparse Modeling . IEEE SigPort. http://sigport.org/2260
Michael Elad, 2017. Sparse Modeling . Available at: http://sigport.org/2260.
Michael Elad. (2017). "Sparse Modeling ." Web.
1. Michael Elad. Sparse Modeling [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2260

Defending DNN Adversarial Attacks with Pruning and Logits Augmentation


Deep neural networks (DNNs) have been shown to be powerful models and perform extremely well on many complicated artificial intelligent tasks. However, recent research found that these powerful models are vulnerable to adversarial attacks, i.e., intentionally added imperceptible perturbations to DNN inputs can easily mislead the DNNs with extremely high confidence.

Paper Details

Authors:
Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin
Submitted On:
28 November 2018 - 9:00pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

GlobalSip_Final.pdf

(30 downloads)

Subscribe

[1] Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin, "Defending DNN Adversarial Attacks with Pruning and Logits Augmentation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3829. Accessed: Jan. 19, 2019.
@article{3829-18,
url = {http://sigport.org/3829},
author = {Siyue Wang; Xiao Wang; Shaokai Ye; Pu Zhao; Xue Lin },
publisher = {IEEE SigPort},
title = {Defending DNN Adversarial Attacks with Pruning and Logits Augmentation},
year = {2018} }
TY - EJOUR
T1 - Defending DNN Adversarial Attacks with Pruning and Logits Augmentation
AU - Siyue Wang; Xiao Wang; Shaokai Ye; Pu Zhao; Xue Lin
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3829
ER -
Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin. (2018). Defending DNN Adversarial Attacks with Pruning and Logits Augmentation. IEEE SigPort. http://sigport.org/3829
Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin, 2018. Defending DNN Adversarial Attacks with Pruning and Logits Augmentation. Available at: http://sigport.org/3829.
Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin. (2018). "Defending DNN Adversarial Attacks with Pruning and Logits Augmentation." Web.
1. Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin. Defending DNN Adversarial Attacks with Pruning and Logits Augmentation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3829

Defending DNN Adversarial Attacks with Pruning and Logits Augmentation


Deep neural networks (DNNs) have been shown to be powerful models and perform extremely well on many complicated artificial intelligent tasks. However, recent research found that these powerful models are vulnerable to adversarial attacks, i.e., intentionally added imperceptible perturbations to DNN inputs can easily mislead the DNNs with extremely high confidence.

Paper Details

Authors:
Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin
Submitted On:
28 November 2018 - 8:40pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

GlobalSip_Final.pptx

(20 downloads)

Subscribe

[1] Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin, "Defending DNN Adversarial Attacks with Pruning and Logits Augmentation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3828. Accessed: Jan. 19, 2019.
@article{3828-18,
url = {http://sigport.org/3828},
author = {Siyue Wang; Xiao Wang; Shaokai Ye; Pu Zhao; Xue Lin },
publisher = {IEEE SigPort},
title = {Defending DNN Adversarial Attacks with Pruning and Logits Augmentation},
year = {2018} }
TY - EJOUR
T1 - Defending DNN Adversarial Attacks with Pruning and Logits Augmentation
AU - Siyue Wang; Xiao Wang; Shaokai Ye; Pu Zhao; Xue Lin
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3828
ER -
Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin. (2018). Defending DNN Adversarial Attacks with Pruning and Logits Augmentation. IEEE SigPort. http://sigport.org/3828
Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin, 2018. Defending DNN Adversarial Attacks with Pruning and Logits Augmentation. Available at: http://sigport.org/3828.
Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin. (2018). "Defending DNN Adversarial Attacks with Pruning and Logits Augmentation." Web.
1. Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, Xue Lin. Defending DNN Adversarial Attacks with Pruning and Logits Augmentation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3828

Set-Theoretic Learning for Detection in Cell-Less C-RAN Systems

Paper Details

Authors:
R.L.G Cavalcante, Zoran Utkovski, Slawomir Stanczak
Submitted On:
28 November 2018 - 12:09pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

GlobalSip 2018

(20 downloads)

Subscribe

[1] R.L.G Cavalcante, Zoran Utkovski, Slawomir Stanczak, "Set-Theoretic Learning for Detection in Cell-Less C-RAN Systems", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3822. Accessed: Jan. 19, 2019.
@article{3822-18,
url = {http://sigport.org/3822},
author = {R.L.G Cavalcante; Zoran Utkovski; Slawomir Stanczak },
publisher = {IEEE SigPort},
title = {Set-Theoretic Learning for Detection in Cell-Less C-RAN Systems},
year = {2018} }
TY - EJOUR
T1 - Set-Theoretic Learning for Detection in Cell-Less C-RAN Systems
AU - R.L.G Cavalcante; Zoran Utkovski; Slawomir Stanczak
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3822
ER -
R.L.G Cavalcante, Zoran Utkovski, Slawomir Stanczak. (2018). Set-Theoretic Learning for Detection in Cell-Less C-RAN Systems. IEEE SigPort. http://sigport.org/3822
R.L.G Cavalcante, Zoran Utkovski, Slawomir Stanczak, 2018. Set-Theoretic Learning for Detection in Cell-Less C-RAN Systems. Available at: http://sigport.org/3822.
R.L.G Cavalcante, Zoran Utkovski, Slawomir Stanczak. (2018). "Set-Theoretic Learning for Detection in Cell-Less C-RAN Systems." Web.
1. R.L.G Cavalcante, Zoran Utkovski, Slawomir Stanczak. Set-Theoretic Learning for Detection in Cell-Less C-RAN Systems [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3822

On The Utility of Conditional Generation Based Mutual Information For Characterizing Adversarial Subspaces

Paper Details

Authors:
Pei-hsuan Lu, Pin-yu Chen, Chia-mu Yu
Submitted On:
8 December 2018 - 5:11am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

On The Utility of Conditional Generation Based Mutual Information For Characterizing Adversarial Subspaces.pdf

(22 downloads)

Subscribe

[1] Pei-hsuan Lu, Pin-yu Chen, Chia-mu Yu, "On The Utility of Conditional Generation Based Mutual Information For Characterizing Adversarial Subspaces", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3820. Accessed: Jan. 19, 2019.
@article{3820-18,
url = {http://sigport.org/3820},
author = {Pei-hsuan Lu; Pin-yu Chen; Chia-mu Yu },
publisher = {IEEE SigPort},
title = {On The Utility of Conditional Generation Based Mutual Information For Characterizing Adversarial Subspaces},
year = {2018} }
TY - EJOUR
T1 - On The Utility of Conditional Generation Based Mutual Information For Characterizing Adversarial Subspaces
AU - Pei-hsuan Lu; Pin-yu Chen; Chia-mu Yu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3820
ER -
Pei-hsuan Lu, Pin-yu Chen, Chia-mu Yu. (2018). On The Utility of Conditional Generation Based Mutual Information For Characterizing Adversarial Subspaces. IEEE SigPort. http://sigport.org/3820
Pei-hsuan Lu, Pin-yu Chen, Chia-mu Yu, 2018. On The Utility of Conditional Generation Based Mutual Information For Characterizing Adversarial Subspaces. Available at: http://sigport.org/3820.
Pei-hsuan Lu, Pin-yu Chen, Chia-mu Yu. (2018). "On The Utility of Conditional Generation Based Mutual Information For Characterizing Adversarial Subspaces." Web.
1. Pei-hsuan Lu, Pin-yu Chen, Chia-mu Yu. On The Utility of Conditional Generation Based Mutual Information For Characterizing Adversarial Subspaces [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3820

Sparse Discriminative Tensor Dictionary Learning for Object Classification

Paper Details

Authors:
Submitted On:
27 November 2018 - 12:57pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Sparse_Discriminative_Tensor_Dictionary_Learning_for_Object_Classification.pdf

(21 downloads)

Subscribe

[1] , "Sparse Discriminative Tensor Dictionary Learning for Object Classification", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3814. Accessed: Jan. 19, 2019.
@article{3814-18,
url = {http://sigport.org/3814},
author = { },
publisher = {IEEE SigPort},
title = {Sparse Discriminative Tensor Dictionary Learning for Object Classification},
year = {2018} }
TY - EJOUR
T1 - Sparse Discriminative Tensor Dictionary Learning for Object Classification
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3814
ER -
. (2018). Sparse Discriminative Tensor Dictionary Learning for Object Classification. IEEE SigPort. http://sigport.org/3814
, 2018. Sparse Discriminative Tensor Dictionary Learning for Object Classification. Available at: http://sigport.org/3814.
. (2018). "Sparse Discriminative Tensor Dictionary Learning for Object Classification." Web.
1. . Sparse Discriminative Tensor Dictionary Learning for Object Classification [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3814

GAN-NL: UNSUPERVISED REPRESENTATION LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION

Paper Details

Authors:
Xiaoming Tao, Mai Xu, Chaoyi Han, Jianhua Lu
Submitted On:
27 November 2018 - 2:22am
Short Link:
Type:
Event:

Document Files

段一平GlobalSIP_poster_final.pdf

(0)

Subscribe

[1] Xiaoming Tao, Mai Xu, Chaoyi Han, Jianhua Lu, "GAN-NL: UNSUPERVISED REPRESENTATION LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3806. Accessed: Jan. 19, 2019.
@article{3806-18,
url = {http://sigport.org/3806},
author = {Xiaoming Tao; Mai Xu; Chaoyi Han; Jianhua Lu },
publisher = {IEEE SigPort},
title = {GAN-NL: UNSUPERVISED REPRESENTATION LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION},
year = {2018} }
TY - EJOUR
T1 - GAN-NL: UNSUPERVISED REPRESENTATION LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION
AU - Xiaoming Tao; Mai Xu; Chaoyi Han; Jianhua Lu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3806
ER -
Xiaoming Tao, Mai Xu, Chaoyi Han, Jianhua Lu. (2018). GAN-NL: UNSUPERVISED REPRESENTATION LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION. IEEE SigPort. http://sigport.org/3806
Xiaoming Tao, Mai Xu, Chaoyi Han, Jianhua Lu, 2018. GAN-NL: UNSUPERVISED REPRESENTATION LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION. Available at: http://sigport.org/3806.
Xiaoming Tao, Mai Xu, Chaoyi Han, Jianhua Lu. (2018). "GAN-NL: UNSUPERVISED REPRESENTATION LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION." Web.
1. Xiaoming Tao, Mai Xu, Chaoyi Han, Jianhua Lu. GAN-NL: UNSUPERVISED REPRESENTATION LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3806

ON THE BEHAVIOR OF THE EXPECTATION-MAXIMIZATION ALGORITHM FOR MIXTURE MODELS

Paper Details

Authors:
Babak Barazandeh, Meisam Razaviyayn
Submitted On:
23 November 2018 - 11:48am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

Globalsip.pdf

(731 downloads)

Subscribe

[1] Babak Barazandeh, Meisam Razaviyayn, "ON THE BEHAVIOR OF THE EXPECTATION-MAXIMIZATION ALGORITHM FOR MIXTURE MODELS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3746. Accessed: Jan. 19, 2019.
@article{3746-18,
url = {http://sigport.org/3746},
author = {Babak Barazandeh; Meisam Razaviyayn },
publisher = {IEEE SigPort},
title = {ON THE BEHAVIOR OF THE EXPECTATION-MAXIMIZATION ALGORITHM FOR MIXTURE MODELS},
year = {2018} }
TY - EJOUR
T1 - ON THE BEHAVIOR OF THE EXPECTATION-MAXIMIZATION ALGORITHM FOR MIXTURE MODELS
AU - Babak Barazandeh; Meisam Razaviyayn
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3746
ER -
Babak Barazandeh, Meisam Razaviyayn. (2018). ON THE BEHAVIOR OF THE EXPECTATION-MAXIMIZATION ALGORITHM FOR MIXTURE MODELS. IEEE SigPort. http://sigport.org/3746
Babak Barazandeh, Meisam Razaviyayn, 2018. ON THE BEHAVIOR OF THE EXPECTATION-MAXIMIZATION ALGORITHM FOR MIXTURE MODELS. Available at: http://sigport.org/3746.
Babak Barazandeh, Meisam Razaviyayn. (2018). "ON THE BEHAVIOR OF THE EXPECTATION-MAXIMIZATION ALGORITHM FOR MIXTURE MODELS." Web.
1. Babak Barazandeh, Meisam Razaviyayn. ON THE BEHAVIOR OF THE EXPECTATION-MAXIMIZATION ALGORITHM FOR MIXTURE MODELS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3746

Deep-learning-based pipe leak detection using image-based leak features

Paper Details

Authors:
Doo-Byung Yoon, Se Won OH, Gwan Joong Kim, Nae-Soo Kim, Cheol-Sig Pyo
Submitted On:
8 October 2018 - 11:29am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster_ICIP2018.pdf

(75 downloads)

Subscribe

[1] Doo-Byung Yoon, Se Won OH, Gwan Joong Kim, Nae-Soo Kim, Cheol-Sig Pyo, "Deep-learning-based pipe leak detection using image-based leak features", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3637. Accessed: Jan. 19, 2019.
@article{3637-18,
url = {http://sigport.org/3637},
author = {Doo-Byung Yoon; Se Won OH; Gwan Joong Kim; Nae-Soo Kim; Cheol-Sig Pyo },
publisher = {IEEE SigPort},
title = {Deep-learning-based pipe leak detection using image-based leak features},
year = {2018} }
TY - EJOUR
T1 - Deep-learning-based pipe leak detection using image-based leak features
AU - Doo-Byung Yoon; Se Won OH; Gwan Joong Kim; Nae-Soo Kim; Cheol-Sig Pyo
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3637
ER -
Doo-Byung Yoon, Se Won OH, Gwan Joong Kim, Nae-Soo Kim, Cheol-Sig Pyo. (2018). Deep-learning-based pipe leak detection using image-based leak features. IEEE SigPort. http://sigport.org/3637
Doo-Byung Yoon, Se Won OH, Gwan Joong Kim, Nae-Soo Kim, Cheol-Sig Pyo, 2018. Deep-learning-based pipe leak detection using image-based leak features. Available at: http://sigport.org/3637.
Doo-Byung Yoon, Se Won OH, Gwan Joong Kim, Nae-Soo Kim, Cheol-Sig Pyo. (2018). "Deep-learning-based pipe leak detection using image-based leak features." Web.
1. Doo-Byung Yoon, Se Won OH, Gwan Joong Kim, Nae-Soo Kim, Cheol-Sig Pyo. Deep-learning-based pipe leak detection using image-based leak features [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3637

Sequential Knowledge Transfer in Teacher-Student Framework using Densely Distilled Flow-Base Information

Paper Details

Authors:
Ji-Hoon Bae, Junho Yim, Nae-Soo Kim, Cheol-Sig Pyo, Junmo Kim
Submitted On:
8 October 2018 - 11:18am
Short Link:
Type:
Event:
Presenter's Name:

Document Files

ICIP_DoyeobYeo.pdf

(40 downloads)

Subscribe

[1] Ji-Hoon Bae, Junho Yim, Nae-Soo Kim, Cheol-Sig Pyo, Junmo Kim, "Sequential Knowledge Transfer in Teacher-Student Framework using Densely Distilled Flow-Base Information", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3636. Accessed: Jan. 19, 2019.
@article{3636-18,
url = {http://sigport.org/3636},
author = {Ji-Hoon Bae; Junho Yim; Nae-Soo Kim; Cheol-Sig Pyo; Junmo Kim },
publisher = {IEEE SigPort},
title = {Sequential Knowledge Transfer in Teacher-Student Framework using Densely Distilled Flow-Base Information},
year = {2018} }
TY - EJOUR
T1 - Sequential Knowledge Transfer in Teacher-Student Framework using Densely Distilled Flow-Base Information
AU - Ji-Hoon Bae; Junho Yim; Nae-Soo Kim; Cheol-Sig Pyo; Junmo Kim
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3636
ER -
Ji-Hoon Bae, Junho Yim, Nae-Soo Kim, Cheol-Sig Pyo, Junmo Kim. (2018). Sequential Knowledge Transfer in Teacher-Student Framework using Densely Distilled Flow-Base Information. IEEE SigPort. http://sigport.org/3636
Ji-Hoon Bae, Junho Yim, Nae-Soo Kim, Cheol-Sig Pyo, Junmo Kim, 2018. Sequential Knowledge Transfer in Teacher-Student Framework using Densely Distilled Flow-Base Information. Available at: http://sigport.org/3636.
Ji-Hoon Bae, Junho Yim, Nae-Soo Kim, Cheol-Sig Pyo, Junmo Kim. (2018). "Sequential Knowledge Transfer in Teacher-Student Framework using Densely Distilled Flow-Base Information." Web.
1. Ji-Hoon Bae, Junho Yim, Nae-Soo Kim, Cheol-Sig Pyo, Junmo Kim. Sequential Knowledge Transfer in Teacher-Student Framework using Densely Distilled Flow-Base Information [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3636

Pages