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 Shu-Tao Xia

TokenPose: Learning Keypoint Tokens for Human Pose Estimation


Apr 09, 2021
Yanjie Li, Shoukui Zhang, Zhicheng Wang, Sen Yang, Wankou Yang, Shu-Tao Xia, Erjin Zhou


  Access Paper or Ask Questions

Backdoor Attack in the Physical World


Apr 06, 2021
Yiming Li, Tongqing Zhai, Yong Jiang, Zhifeng Li, Shu-Tao Xia

* This work was done when Yiming Li was an intern at Tencent AI Lab, supported by the Tencent Rhino-Bird Elite Training Program (2020). This is a 6-pages short version of our ongoing work, `Rethinking the Trigger of Backdoor Attack' (arXiv:2004.04692). It is accepted by the non-archival ICLR 2021 workshop on Robust and Reliable Machine Learning in the Real World 

  Access Paper or Ask Questions

Hidden Backdoor Attack against Semantic Segmentation Models


Apr 03, 2021
Yiming Li, Yanjie Li, Yalei Lv, Yong Jiang, Shu-Tao Xia

* This is a 6-pages short version of our ongoing work. It is accepted by the non-archival ICLR workshop on Security and Safety in Machine Learning Systems, 2021. The first two authors contributed equally to this work 

  Access Paper or Ask Questions

Improving Adversarial Robustness via Channel-wise Activation Suppressing


Mar 11, 2021
Yang Bai, Yuyuan Zeng, Yong Jiang, Shu-Tao Xia, Xingjun Ma, Yisen Wang

* ICLR2021 accepted paper 

  Access Paper or Ask Questions

Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits


Feb 21, 2021
Jiawang Bai, Baoyuan Wu, Yong Zhang, Yiming Li, Zhifeng Li, Shu-Tao Xia

* Accepted by ICLR 2021 

  Access Paper or Ask Questions

Backdoor Attack against Speaker Verification


Oct 25, 2020
Tongqing Zhai, Yiming Li, Ziqi Zhang, Baoyuan Wu, Yong Jiang, Shu-Tao Xia

* The first two authors contributed equally to this work. 5 pages 

  Access Paper or Ask Questions

JSRT: James-Stein Regression Tree


Oct 21, 2020
Xingchun Xiang, Qingtao Tang, Huaixuan Zhang, Tao Dai, Jiawei Li, Shu-Tao Xia

* 7 pages 

  Access Paper or Ask Questions

DPAttack: Diffused Patch Attacks against Universal Object Detection


Oct 16, 2020
Shudeng Wu, Tao Dai, Shu-Tao Xia

* 4 pages, 2 figures, CIKM Workshop 

  Access Paper or Ask Questions

Open-sourced Dataset Protection via Backdoor Watermarking


Oct 12, 2020
Yiming Li, Ziqi Zhang, Jiawang Bai, Baoyuan Wu, Yong Jiang, Shu-Tao Xia

* 6 pages 

  Access Paper or Ask Questions

Improving Query Efficiency of Black-box Adversarial Attack


Sep 25, 2020
Yang Bai, Yuyuan Zeng, Yong Jiang, Yisen Wang, Shu-Tao Xia, Weiwei Guo

* Accepted to ECCV2020 

  Access Paper or Ask Questions

Rectified Decision Trees: Exploring the Landscape of Interpretable and Effective Machine Learning


Aug 21, 2020
Yiming Li, Jiawang Bai, Jiawei Li, Xue Yang, Yong Jiang, Shu-Tao Xia

* 9 pages. The first two authors contribute equally to this work. arXiv admin note: text overlap with arXiv:1903.05965 

  Access Paper or Ask Questions

Backdoor Learning: A Survey


Aug 21, 2020
Yiming Li, Baoyuan Wu, Yong Jiang, Zhifeng Li, Shu-Tao Xia

* 11 pages. A curated list of backdoor learning resources in this paper is presented in the Github Repo (https://github.com/THUYimingLi/backdoor-learning-resources). We will try our best to continuously maintain the repo 

  Access Paper or Ask Questions

Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters


Jul 16, 2020
Haoyu Liang, Zhihao Ouyang, Yuyuan Zeng, Hang Su, Zihao He, Shu-Tao Xia, Jun Zhu, Bo Zhang

* 14pages (except appendix and reference), 9 figures, 3 tables 

  Access Paper or Ask Questions

Matrix Smoothing: A Regularization for DNN with Transition Matrix under Noisy Labels


Mar 26, 2020
Xianbin Lv, Dongxian Wu, Shu-Tao Xia

* ICME 2020 

  Access Paper or Ask Questions

Practical and Bilateral Privacy-preserving Federated Learning


Feb 25, 2020
Yan Feng, Xue Yang, Weijun Fang, Shu-Tao Xia, Xiaohu Tang

* Submitted to ICML 2020 

  Access Paper or Ask Questions

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets


Feb 14, 2020
Dongxian Wu, Yisen Wang, Shu-Tao Xia, James Bailey, Xingjun Ma

* ICLR 2020 conference paper (spotlight) 

  Access Paper or Ask Questions

Deep Flow Collaborative Network for Online Visual Tracking


Nov 05, 2019
Peidong Liu, Xiyu Yan, Yong Jiang, Shu-Tao Xia


  Access Paper or Ask Questions

Visual Privacy Protection via Mapping Distortion


Nov 05, 2019
Peidong Liu, Yiming Li, Yong Jiang, Shu-Tao Xia


  Access Paper or Ask Questions

Adversarial Defense Via Local Flatness Regularization


Oct 27, 2019
Jia Xu, Yiming Li, Yang Bai, Yong Jiang, Shu-Tao Xia

* 4 pages 

  Access Paper or Ask Questions

Adaptive Regularization of Labels


Aug 15, 2019
Qianggang Ding, Sifan Wu, Hao Sun, Jiadong Guo, Shu-Tao Xia


  Access Paper or Ask Questions

Dimensionality-Driven Learning with Noisy Labels


Jul 31, 2018
Xingjun Ma, Yisen Wang, Michael E. Houle, Shuo Zhou, Sarah M. Erfani, Shu-Tao Xia, Sudanthi Wijewickrema, James Bailey

* In Proceedings of the International Conference on Machine Learning (ICML), 2018 

  Access Paper or Ask Questions

Iterative Learning with Open-set Noisy Labels


Mar 31, 2018
Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey, Hongyuan Zha, Le Song, Shu-Tao Xia

* CVPR2018-Spotlight 

  Access Paper or Ask Questions

Unifying Decision Trees Split Criteria Using Tsallis Entropy


Aug 23, 2016
Yisen Wang, Chaobing Song, Shu-Tao Xia

* 6 pages, 2 figures 

  Access Paper or Ask Questions

Nonextensive information theoretical machine


Apr 21, 2016
Chaobing Song, Shu-Tao Xia


  Access Paper or Ask Questions