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 Lixin Fan

FedIPR: Ownership Verification for Federated Deep Neural Network Models


Sep 27, 2021
Lixin Fan, Bowen Li, Hanlin Gu, Jie Li, Qiang Yang

* 23 pages, 12 figures 

  Access Paper or Ask Questions

Federated Deep Learning with Bayesian Privacy


Sep 27, 2021
Hanlin Gu, Lixin Fan, Bowen Li, Yan Kang, Yuan Yao, Qiang Yang


  Access Paper or Ask Questions

Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI


Jul 26, 2021
Quanshi Zhang, Tian Han, Lixin Fan, Zhanxing Zhu, Hang Su, Ying Nian Wu, Jie Ren, Hao Zhang


  Access Paper or Ask Questions

ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment


Jul 12, 2021
Chun Chet Ng, Akmalul Khairi Bin Nazaruddin, Yeong Khang Lee, Xinyu Wang, Yuliang Liu, Chee Seng Chan, Lianwen Jin, Yipeng Sun, Lixin Fan

* International Conference on Document Analysis and Recognition (ICDAR) 2021 
* Technical report of ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment 

  Access Paper or Ask Questions

Ternary Hashing


Mar 19, 2021
Chang Liu, Lixin Fan, Kam Woh Ng, Yilun Jin, Ce Ju, Tianyu Zhang, Chee Seng Chan, Qiang Yang


  Access Paper or Ask Questions

Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack


Mar 01, 2021
Ding Sheng Ong, Chee Seng Chan, Kam Woh Ng, Lixin Fan, Qiang Yang

* Accepted at CVPR2021 

  Access Paper or Ask Questions

Rethinking Uncertainty in Deep Learning: Whether and How it Improves Robustness


Nov 27, 2020
Yilun Jin, Lixin Fan, Kam Woh Ng, Ce Ju, Qiang Yang


  Access Paper or Ask Questions

Protect, Show, Attend and Tell: Image Captioning Model with Ownership Protection


Aug 25, 2020
Jian Han Lim, Chee Seng Chan, Kam Woh Ng, Lixin Fan, Qiang Yang

* 9 pages 

  Access Paper or Ask Questions

Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks


Jun 23, 2020
Lixin Fan, Kam Woh Ng, Ce Ju, Tianyu Zhang, Chang Liu, Chee Seng Chan, Qiang Yang

* under review, 36 pages (updated Eq. 3 and Fig. 8) 

  Access Paper or Ask Questions

L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition


Oct 25, 2019
Yuanfeng Song, Di Jiang, Xuefang Zhao, Qian Xu, Raymond Chi-Wing Wong, Lixin Fan, Qiang Yang

* 5 pages, 3 figures 

  Access Paper or Ask Questions

Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks


Sep 21, 2019
Lixin Fan, Kam Woh Ng, Chee Seng Chan

* This paper is accepted by NeurIPS 2019; Our code is available at https://github.com/kamwoh/DeepIPR. This version updates Figure 2&5 and email of first author 

  Access Paper or Ask Questions

Simultaneously Learning Architectures and Features of Deep Neural Networks


Jun 11, 2019
Tinghuai Wang, Lixin Fan, Huiling Wang


  Access Paper or Ask Questions

Digital Passport: A Novel Technological Strategy for Intellectual Property Protection of Convolutional Neural Networks


May 10, 2019
Lixin Fan, KamWoh Ng, Chee Seng Chan

* This paper proposes a new timely IPR solution that embed digital passports into CNN models to prevent the unauthorized network usage (i.e. infringement) by paralyzing the networks while maintaining its functionality for verified users 

  Access Paper or Ask Questions

Fast Registration for cross-source point clouds by using weak regional affinity and pixel-wise refinement


Mar 11, 2019
Xiaoshui Huang, Lixin Fan, Qiang Wu, Jian Zhang, Chun Yuan

* ICME 2019 

  Access Paper or Ask Questions

Proceedings of AAAI 2019 Workshop on Network Interpretability for Deep Learning


Jan 25, 2019
Quanshi Zhang, Lixin Fan, Bolei Zhou


  Access Paper or Ask Questions

A Universal Logic Operator for Interpretable Deep Convolution Networks


Jan 20, 2019
KamWoh Ng, Lixin Fan, Chee Seng Chan

* In AAAI-19 Workshop on Network Interpretability for Deep Learning 

  Access Paper or Ask Questions

Depth Masked Discriminative Correlation Filter


Oct 10, 2018
Uğur Kart, Joni-Kristian Kämäräinen, Jiří Matas, Lixin Fan, Francesco Cricri

* 6 pages, accepted to ICPR 2018. \copyright 2018 IEEE 

  Access Paper or Ask Questions

Memory-Efficient Deep Salient Object Segmentation Networks on Gridized Superpixels


May 22, 2018
Caglar Aytekin, Xingyang Ni, Francesco Cricri, Lixin Fan, Emre Aksu

* 6 pages, submitted to MMSP 2018 

  Access Paper or Ask Questions

Object Detection in Equirectangular Panorama


May 21, 2018
Wenyan Yang, Yanlin Qian, Francesco Cricri, Lixin Fan, Joni-Kristian Kamarainen

* 6 pages 

  Access Paper or Ask Questions

A Theoretical Investigation of Graph Degree as an Unsupervised Normality Measure


Feb 05, 2018
Caglar Aytekin, Francesco Cricri, Lixin Fan, Emre Aksu

* Submitted to IJCAI 2018 

  Access Paper or Ask Questions

Deep Epitome for Unravelling Generalized Hamming Network: A Fuzzy Logic Interpretation of Deep Learning


Nov 15, 2017
Lixin Fan

* 25 pages, 14 figures 

  Access Paper or Ask Questions

Revisit Fuzzy Neural Network: Demystifying Batch Normalization and ReLU with Generalized Hamming Network


Oct 27, 2017
Lixin Fan

* 10 pages, 5 figures, NIPS 2017 

  Access Paper or Ask Questions

Happy Travelers Take Big Pictures: A Psychological Study with Machine Learning and Big Data


Sep 22, 2017
Xuefeng Liang, Lixin Fan, Yuen Peng Loh, Yang Liu, Song Tong


  Access Paper or Ask Questions

A coarse-to-fine algorithm for registration in 3D street-view cross-source point clouds


Oct 24, 2016
Xiaoshui Huang, Jian Zhang, Qiang Wu, Lixin Fan, Chun Yuan


  Access Paper or Ask Questions

A Systematic Approach for Cross-source Point Cloud Registration by Preserving Macro and Micro Structures


Aug 22, 2016
Xiaoshui Huang, Jian Zhang, Lixin Fan, Qiang Wu, Chun Yuan

* Cross-source point cloud registration 

  Access Paper or Ask Questions