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 Gavin Weiguang Ding

CDT: Cascading Decision Trees for Explainable Reinforcement Learning

Nov 15, 2020
Zihan Ding, Pablo Hernandez-Leal, Gavin Weiguang Ding, Changjian Li, Ruitong Huang

  Access Paper or Ask Questions

Cascaded Deep Neural Networks for Retinal Layer Segmentation of Optical Coherence Tomography with Fluid Presence

Dec 07, 2019
Donghuan Lu, Morgan Heisler, Da Ma, Setareh Dabiri, Sieun Lee, Gavin Weiguang Ding, Marinko V. Sarunic, Mirza Faisal Beg

  Access Paper or Ask Questions

On the Effectiveness of Low Frequency Perturbations

Feb 28, 2019
Yash Sharma, Gavin Weiguang Ding, Marcus Brubaker

  Access Paper or Ask Questions

On the Sensitivity of Adversarial Robustness to Input Data Distributions

Feb 22, 2019
Gavin Weiguang Ding, Kry Yik Chau Lui, Xiaomeng Jin, Luyu Wang, Ruitong Huang

* ICLR 2019, Seventh International Conference on Learning Representations 

  Access Paper or Ask Questions

advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch

Feb 20, 2019
Gavin Weiguang Ding, Luyu Wang, Xiaomeng Jin

  Access Paper or Ask Questions

Max-Margin Adversarial (MMA) Training: Direct Input Space Margin Maximization through Adversarial Training

Dec 06, 2018
Gavin Weiguang Ding, Yash Sharma, Kry Yik Chau Lui, Ruitong Huang

  Access Paper or Ask Questions

Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds

Oct 31, 2018
Kry Yik Chau Lui, Gavin Weiguang Ding, Ruitong Huang, Robert J. McCann

* Neural Information Processing Systems (NIPS 2018) 
* 32nd Conference on Neural Information Processing Systems (NIPS 2018), Montreal, Canada 

  Access Paper or Ask Questions

Improving GAN Training via Binarized Representation Entropy (BRE) Regularization

May 09, 2018
Yanshuai Cao, Gavin Weiguang Ding, Kry Yik-Chau Lui, Ruitong Huang

* Published as a conference paper at the 6th International Conference on Learning Representations (ICLR 2018) 

  Access Paper or Ask Questions