Haofan Wang

Computer Vision Engineer
Work Email: wanghaofan (at) kuaishou.com
School Email: haofanw (at) alumni.cmu.edu
Personal Email: haofanwang.ai (at) gmail.com
Research Interests
  • Contrastive Learning
  • Cross-Modal Pre-training
  • Self-Supervised Learning
  • Interpretable Machine Learning
Biography

Haofan Wang (王浩帆) is a computer vision engineer at MMU of Kuaishou Technology, supervised by Dr. Debing Zhang on cross-modal retrieval. Before joined Kuaishou, he graduated from Carnegie Mellon University in December 2020, advised by Dr. Piotr (Peter) Mardziel. Previously, he worked as a research intern with Prof. Bernard Ghanem at KAUST (2020 Summer) and Prof. Xia (Ben) Hu at Texas A&M University (2019 Summer). He obtained undergraduate degree from Dalian Maritime University in June 2019 and exchanged at UC Berkeley (worked at RISE Lab, Clipper Group) in 2017 Fall. He also worked at OpenMined, RealAI, Everspry, Horizon Robotics and Institute of Software Chinese Academy of Sciences.

I have a plan to apply for a Ph.D. position started in 2023 Spring/Fall, if you are interested in my background and have positions, please don't hesitate to contact me! Outside work, I am also open to research discussion or work opportunities, find me via haofanwang.ai@gmail.com.

News
  • [06/2021]: One abstract is accepted to RCV workshop at CVPR 2021! The full paper is accepted to PPML at ACM CCS 2021!
  • [12/2020]: I moved from CMU to MMU of Kuaishou Technology as software engineer!
  • [11/2020]: One paper is accepted to SpicyFL workshop at NeurIPS 2020!
  • [09/2020]: One paper accepted to NeurIPS 2020!
  • [04/2020]: One paper accepted to TCV workshop at CVPR 2020!
    • Projects
    [crop]
    CropImage: A toolkit for detecting and cropping main part from pictures.
    [Project Page] [Demo]
    Selected Publications (Full List)
    [clip]
    EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling
    Jue Wang, Haofan Wang*, Jincan Deng, Weijia Wu, Debing Zhang.
    Pre-print, Under Review
    [Paper]
    [scipy]
    When Differential Privacy Meets Interpretability: A Case Study
    Rakshit Naidu, Aman Priyanshu, Aadith Kumar, Sasikanth Kotti, Haofan Wang*, Fatemehsadat Mireshghallah
    IEEE CVPR 2021 Workshop on Responsible Computer Vision, Poster
    [Paper] [Poster]
    [scipy]
    Selective Federated Transfer Learning using Representation Similarity
    Tushar Semwal, Haofan Wang*, Chinnakotla Krishna Teja Reddy.
    NeurIPS 2020 Workshop on Scalability, Privacy, and Security in Federated Learning, Poster
    [Paper]
    [smooth]
    Smoothed Geometry for Robust Attribution
    Zifan Wang, Haofan Wang*, Shakul Ramkumar, Matt Fredrikson, Piotr Mardziel, and Anupam Datta
    NeurIPS 2020, Poster
    [Paper] [Poster] [Code] [Citation: 6]
    [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] [Slides] [News] [Citation: 133]
    [HeadPose]
    Hybrid Coarse-fine Classification for Head Pose Estimation
    Haofan Wang*, Zhenghua Chen, and Yi Zhou,
    ArXiv 1901.06778
    [Project Page] [Paper] [Citation: 4]
    Talks
  • [06/2021] MMU, Kuaishou. An Overview of Large Scale Pre-Training
    • Teaching
  • TA of 18-793 Image and Video Processing, Summer 2020, Carnegie Mellon University
    • Professional Services
  • Conference Reviewer: NeurIPS'21, ICLR'22
    • Trajectory

    DMU (Bachelor) --> CMU (Master) --> MMU (Engineer) --> What's NeXT?