[Pingchuan :)]

Haofan Wang

First-Year graduate student, CMU
Email: haofanw (at) andrew.cmu.edu
Research Interests
  • Computer Vision
  • Graph Neural Network
  • Explainable Neural Network
  • Adversarial Attack and Robustness
Biography

Haofan Wang (王浩帆) is a first-year graduate student at College of Engineering, Carnegie Mellon University, advised by Prof. Piotr (Peter) Mardziel. Previously, he worked with Prof. Xia (Ben) Hu at Texas A&M University. He obtained undergraduate degree from Dalian Maritime University. He has also spent time at RealAI, Everspry, Horizon Robotics, Institute of Software Chinese Academy of Sciences and UC Berkeley.

News

2020.4.12: Our paper "Score-CAM" has been accepted to CVPR 2020 Workshop!

Publications
[smooth]
Smoothed Geometry for Robust Attribution
Zifan Wang, Haofan Wang*, Shakul Ramkumar, Matt Fredrikson, Piotr Mardziel, and Anupam Datta
Under Review
[Paper]
[Score-CAM]
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
Haofan Wang*, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel and Xia (Ben) Hu
IEEE CVPR 2020 Workshop on Fair, Data Efficient and Trusted Computer Vision
[Project Page] [Paper]
[HeadPose]
Hybrid Coarse-fine Classification for Head Pose Estimation
Haofan Wang*, Zhenghua Chen, and Yi Zhou,
ArXiv 1901.06778
[Project Page] [Paper]