Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Shujian Yu

Deep Deterministic Information Bottleneck with Matrix-based Entropy Functional


Jan 31, 2021
Xi Yu, Shujian Yu, Jose C. Principe

* Accepted at ICASSP-21. Code available at https://github.com/yuxi120407/DIB. Extended version of the suppelementary material in "Measuring the Dependence with Matrix-based Entropy Functional", AAAI-21, arXiv:2101.10160 

  Access Paper or Ask Questions

Measuring Dependence with Matrix-based Entropy Functional


Jan 25, 2021
Shujian Yu, Francesco Alesiani, Xi Yu, Robert Jenssen, Jose C. Principe

* Accepted at AAAI-21. An interpretable and differentiable dependence (or independence) measure that can be used to 1) train deep network under covariate shift and non-Gaussian noise; 2) implement a deep deterministic information bottleneck; and 3) understand the dynamics of learning of CNN. Code available at https://bit.ly/AAAI-dependence 

  Access Paper or Ask Questions

Modular-Relatedness for Continual Learning


Nov 02, 2020
Ammar Shaker, Shujian Yu, Francesco Alesiani


  Access Paper or Ask Questions

Bilevel Continual Learning


Nov 02, 2020
Ammar Shaker, Francesco Alesiani, Shujian Yu, Wenzhe Yin


  Access Paper or Ask Questions

Learning an Interpretable Graph Structure in Multi-Task Learning


Sep 11, 2020
Shujian Yu, Francesco Alesiani, Ammar Shaker, Wenzhe Yin

* 11 pages, 7 figures 

  Access Paper or Ask Questions

Towards Interpretable Multi-Task Learning Using Bilevel Programming


Sep 11, 2020
Francesco Alesiani, Shujian Yu, Ammar Shaker, Wenzhe Yin

* Manuscript accepted at ECML PKDD 2020 

  Access Paper or Ask Questions

PRI-VAE: Principle-of-Relevant-Information Variational Autoencoders


Jul 13, 2020
Yanjun Li, Shujian Yu, Jose C. Principe, Xiaolin Li, Dapeng Wu


  Access Paper or Ask Questions

Modularizing Deep Learning via Pairwise Learning With Kernels


May 12, 2020
Shiyu Duan, Shujian Yu, Jose Principe


  Access Paper or Ask Questions

Measuring the Discrepancy between Conditional Distributions: Methods, Properties and Applications


May 05, 2020
Shujian Yu, Ammar Shaker, Francesco Alesiani, Jose C. Principe

* accepted at IJCAI 20, code is available at https://github.com/SJYuCNEL/Bregman-Correntropy-Conditional-Divergence 

  Access Paper or Ask Questions

Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernels


Sep 25, 2019
Kristoffer Wickstrøm, Sigurd Løkse, Michael Kampffmeyer, Shujian Yu, Jose Principe, Robert Jenssen

* 15 pages, 8 figures 

  Access Paper or Ask Questions

Multiscale Principle of Relevant Information for Hyperspectral Image Classification


Jul 13, 2019
Yantao Wei, Shujian Yu, Jose C. Principe


  Access Paper or Ask Questions

Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation


May 29, 2019
Zhengqiang Zhang, Shujian Yu, Shi Yin, Qinmu Peng, Xinge You


  Access Paper or Ask Questions

Simple stopping criteria for information theoretic feature selection


Nov 29, 2018
Shujian Yu, Jose C. Principe

* 4 pages, 2 figures 

  Access Paper or Ask Questions

Robust Visual Tracking using Multi-Frame Multi-Feature Joint Modeling


Nov 19, 2018
Peng Zhang, Shujian Yu, Jiamiao Xu, Xinge You, Xiubao Jiang, Xiao-Yuan Jing, Dacheng Tao

* This paper has been accepted by IEEE Transactions on Circuits and Systems for Video Technology. The MATLAB code of our method is available from our project homepage http://bmal.hust.edu.cn/project/KMF2JMTtracking.html 

  Access Paper or Ask Questions

Understanding Convolutional Neural Network Training with Information Theory


Oct 12, 2018
Shujian Yu, Kristoffer Wickstrøm, Robert Jenssen, Jose C. Principe

* substantial improvement over v1 

  Access Paper or Ask Questions

Coarse-to-Fine Salient Object Detection with Low-Rank Matrix Recovery


Oct 02, 2018
Qi Zheng, Shujian Yu, Xinge You, Qinmu Peng, Wei Yuan

* 32 pages, 9 figures 

  Access Paper or Ask Questions

Concept Drift Detection and Adaptation with Hierarchical Hypothesis Testing


Sep 17, 2018
Shujian Yu, Zubin Abraham, Heng Wang, Mohak Shah, Yantao Wei, José C. Príncipe

* 18 pages, 11 figures 

  Access Paper or Ask Questions

Understanding Autoencoders with Information Theoretic Concepts


Aug 23, 2018
Shujian Yu, Jose C. Principe

* 64 pages, 16 figures 

  Access Paper or Ask Questions

Multivariate Extension of Matrix-based Renyi's α-order Entropy Functional


Aug 23, 2018
Shujian Yu, Luis Gonzalo Sanchez Giraldo, Robert Jenssen, Jose C. Principe

* 26 pages, 8 figures 

  Access Paper or Ask Questions

Request-and-Reverify: Hierarchical Hypothesis Testing for Concept Drift Detection with Expensive Labels


Jun 28, 2018
Shujian Yu, Xiaoyang Wang, Jose C. Principe

* Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (2018) 3033-3039 
* Published as a conference paper at IJCAI 2018 

  Access Paper or Ask Questions

Multi-view Hybrid Embedding: A Divide-and-Conquer Approach


Apr 19, 2018
Jiamiao Xu, Shujian Yu, Xinge You, Mengjun Leng, Xiao-Yuan Jing, C. L. Philip Chen


  Access Paper or Ask Questions

Marine Animal Classification with Correntropy Loss Based Multi-view Learning


May 03, 2017
Zheng Cao, Shujian Yu, Bing Ouyang, Fraser Dalgleish, Anni Vuorenkoski, Gabriel Alsenas, Jose Principe


  Access Paper or Ask Questions