Jun Huan

Parameter-Free Style Projection for Arbitrary Style Transfer

Mar 17, 2020
Siyu Huang, Haoyi Xiong, Tianyang Wang, Qingzhong Wang, Zeyu Chen, Jun Huan, Dejing Dou

* 9 pages, 12 figures

Access Model/Code and Paper

Ultrafast Photorealistic Style Transfer via Neural Architecture Search

Dec 05, 2019
Jie An, Haoyi Xiong, Jun Huan, Jiebo Luo

Access Model/Code and Paper

SecureGBM: Secure Multi-Party Gradient Boosting

Nov 27, 2019
Zhi Fengy, Haoyi Xiong, Chuanyuan Song, Sijia Yang, Baoxin Zhao, Licheng Wang, Zeyu Chen, Shengwen Yang, Liping Liu, Jun Huan

* The first two authors contributed equally to the manuscript. The paper has been accepted for publication in IEEE BigData 2019

Access Model/Code and Paper

Towards Making Deep Transfer Learning Never Hurt

Nov 18, 2019
Ruosi Wan, Haoyi Xiong, Xingjian Li, Zhanxing Zhu, Jun Huan

* accapted as long paper at the 19th IEEE International Conference on Data Mining, 2019
* 10 pages

Access Model/Code and Paper

NormLime: A New Feature Importance Metric for Explaining Deep Neural Networks

Oct 15, 2019
Isaac Ahern, Adam Noack, Luis Guzman-Nateras, Dejing Dou, Boyang Li, Jun Huan

Access Model/Code and Paper

Improving Adversarial Robustness via Attention and Adversarial Logit Pairing

Aug 23, 2019
Dou Goodman, Xingjian Li, Jun Huan, Tao Wei

Access Model/Code and Paper

Fast Universal Style Transfer for Artistic and Photorealistic Rendering

Jul 06, 2019
Jie An, Haoyi Xiong, Jiebo Luo, Jun Huan, Jinwen Ma

Access Model/Code and Paper

AGAN: Towards Automated Design of Generative Adversarial Networks

Jun 25, 2019
Hanchao Wang, Jun Huan

Access Model/Code and Paper

The Multiplicative Noise in Stochastic Gradient Descent: Data-Dependent Regularization, Continuous and Discrete Approximation

Jun 18, 2019
Jingfeng Wu, Wenqing Hu, Haoyi Xiong, Jun Huan, Zhanxing Zhu

Access Model/Code and Paper

StyleNAS: An Empirical Study of Neural Architecture Search to Uncover Surprisingly Fast End-to-End Universal Style Transfer Networks

Jun 06, 2019
Jie An, Haoyi Xiong, Jinwen Ma, Jiebo Luo, Jun Huan

Access Model/Code and Paper

An Empirical Study on Regularization of Deep Neural Networks by Local Rademacher Complexity

Feb 14, 2019
Yingzhen Yang, Xingjian Li, Jun Huan

* Updated the link to the open source PaddlePaddle code of LRC Regularization

Access Model/Code and Paper

FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary

Feb 13, 2019
Yingzhen Yang, Nebojsa Jojic, Jun Huan

Access Model/Code and Paper

DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks

Jan 26, 2019
Xingjian Li, Haoyi Xiong, Hanchao Wang, Yuxuan Rao, Liping Liu, Jun Huan

* Accepted at ICLR 2019

Access Model/Code and Paper

Quasi-potential as an implicit regularizer for the loss function in the stochastic gradient descent

Jan 18, 2019
Wenqing Hu, Zhanxing Zhu, Haoyi Xiong, Jun Huan

* first and preliminary version

Access Model/Code and Paper

Instance-based Deep Transfer Learning

Sep 08, 2018
Tianyang Wang, Jun Huan, Michelle Zhu

Access Model/Code and Paper

Data Dropout: Optimizing Training Data for Convolutional Neural Networks

Sep 07, 2018
Tianyang Wang, Jun Huan, Bo Li

Access Model/Code and Paper

Discriminatory Transfer

Aug 07, 2017
Chao Lan, Jun Huan

* Presented as a poster at the 2017 Workshop on Fairness, Accountability, and Transparency in Machine Learning (FAT/ML 2017)

Access Model/Code and Paper

On the Unreported-Profile-is-Negative Assumption for Predictive Cheminformatics

Aug 07, 2017
Chao Lan, Sai Nivedita Chandrasekaran, Jun Huan

* the quality of the current version is unsatisfactory. we decide to withdraw the manuscript. thank you

Access Model/Code and Paper

Learning Social Circles in Ego Networks based on Multi-View Social Graphs

Dec 24, 2016
Chao Lan, Yuhao Yang, Xiaoli Li, Bo Luo, Jun Huan

* This paper has been withdrawn by the author due to its current unsatisfactory quality

Access Model/Code and Paper