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 Lue Tao

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise

Jun 21, 2021
Hongxin Wei, Lue Tao, Renchunzi Xie, Bo An

  Access Paper or Ask Questions

Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries

Mar 27, 2021
Kun-Peng Ning, Lue Tao, Songcan Chen, Sheng-Jun Huang

* To be published in AAAI-21 

  Access Paper or Ask Questions

Provable Defense Against Delusive Poisoning

Feb 09, 2021
Lue Tao, Lei Feng, Jinfeng Yi, Sheng-Jun Huang, Songcan Chen

  Access Paper or Ask Questions

With False Friends Like These, Who Can Have Self-Knowledge?

Dec 29, 2020
Lue Tao, Songcan Chen

* Preprint (Under review). In this paper, we were the first to introduce the notion of hypocritical examples (inputs perturbed to correct model prediction). This manuscript was first published at OpenReview on September 28, 2020. Please see 

  Access Paper or Ask Questions

Accelerated Stochastic Gradient-free and Projection-free Methods

Aug 10, 2020
Feihu Huang, Lue Tao, Songcan Chen

* Accepted to ICML 2020, 34 pages 

  Access Paper or Ask Questions

Visual and Semantic Prototypes-Jointly Guided CNN for Generalized Zero-shot Learning

Aug 14, 2019
Chuanxing Geng, Lue Tao, Songcan Chen

  Access Paper or Ask Questions