Photo

Yabin Zhang (张亚斌)


I got the PhD degree in Computer Science at The Hong Kong Polytechnic University, under the supervision of Prof. Lei Zhang. I received my Master's and Bachelor's degrees from South China University of Technology, mentored by Prof. Kui Jia.

Research Field: Machine Learning | Computer Vision | Vision-Language Models | OOD Generalization and Detection

Email: ybzhang815@gmail.com; 20113441r@connect.polyu.hk

Other Link: [Google Scholar] [Github] [Zhihu]

Upcoming Graduation: I am nearing the completion of my PhD studies and am currently looking for research positions. Feel free to contact me via email.

News



  • [10/2024] NEW I have passed my PhD oral defense!
  • [09/2024] Our work AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models gets accepted to NeurIPS 2024. [Paper][Code]
  • [07/2024] Two papers have been accepted by ECCV 2024:
  • [03/2024] Our work DMN for versatile adaptation of vision-language models gets accepted to CVPR 2024. [Paper][Code]

  • Education


    2021.01 - Now

    The Hong Kong Polytechnic University
    PhD of Computing, Advisor: Prof. Lei Zhang

    2017.09 - 2020.06

    South China University of Technology, Guangzhou, China
    Master of Signal and Information Processing, Advisor: Prof. Kui Jia

    2013.09 - 2017.06

    South China University of Technology, Guangzhou, China
    Bachelor of Electronic and Information Engineering

    Pre-Prints


    Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning
    Under Review.

    Selected Publications


    Unsupervised multi-class domain adaptation: Theory, algorithms, and practice
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2022
    Exact feature distribution matching for arbitrary style transfer and domain generalization
    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR Oral). 2022
    Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models
    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR). 2024
    Label propagation with augmented anchors: A simple semi-supervised learning baseline for unsupervised domain adaptation
    European Conference on Computer Vision (ECCV Spotlight). 2022
    Domain-symmetric networks for adversarial domain adaptation
    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR). 2019
    Fine-grained visual categorization using meta-learning optimization with sample selection of auxiliary data
    European Conference on Computer Vision (ECCV). 2018
    Part-aware fine-grained object categorization using weakly supervised part detection network
    IEEE Transactions on Multimedia (TMM).
    Unsupervised Domain Adaptation of Black-Box Source Models
    British Machine Vision Conference (BMVC). 2021

    Services



    Program Committee/Reviewers: CVPR, ICCV, ECCV, ICML, ICLR, NeurIPS, SIGGRAPH, AAAI, IJCV, TIP, TMM, TNNLS, TMLR.