Qi Wei (魏琦)

I am currently a research assistant at the School of Computer Science and Engineering (SCSE), Nanyang Technological University (NTU), Singapore, supervised by Prof. Lei Feng and Bo An.

My research interests include computer vision and machine learning, such as Learning with noisy labels, Semi-supervised Learning, Meta-learning, and Partial-label learning. Feel free to email me if you are interested in talking with me.

Email: qi.wei@ntu.edu.sg

[Google scholar] [Github]

News

  • [2024.05] One paper is accepted by ICML 2024.

  • [2024.03] One paper is accepted by TCDS.

  • [2023.09] One paper is accepted by Machine Learning.

  • [2023.04] One Chinese paper is accepted by SCIENTIA SINICA Informationis.

  • [2023.02] One paper is accepted by CVPR 2023.

  • [2023.01] A list of awesome partial-label learning papers and codes is released.

  • [2022.07] One paper is accepted by ECCV 2022.

  • [2021.11] One paper is accepted by Pattern Recognition.

Publications

    (* indicates equal contribution)
  • Jiahan Zhang*, Qi Wei*, Feng Liu, Lei Feng
    Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data.
    International Conference on Machine Learning (ICML) 2024.
  • Qi Wei, Lei Feng, Haoliang Sun, Ren Wang, Rundong He, Yilong Yin.
    Learning Sample-Aware Threshold for Semi-Supervised Learning.
    Machine Learning (MLJ) 2023.
  • Qi Wei, Lei Feng, Haoliang Sun, Chenhui Guo, Ren Wang, Yilong Yin.
    Fine-Grained Classification with Noisy Labels.
    In proc. of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023.
  • Qi Wei, Haoliang Sun, Xiankai Lu, Yilong Yin.
    Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization.
    In proc. of European Conference on Computer Vision (ECCV) 2022.
  • Haoliang Sun*, Chenhui Guo*, Qi Wei, Zhongyi Han, Yilong Yin.
    Learning to Rectify for Robust Learning with Noisy Labels.
    Pattern Recognition (PR) 2022.
  • Qi Wei, Haoliang Sun, Yuling Ma, Yilong Yin.
    A Joint Training Framework for Learning with Noisy Labels.
    SCIENTIA SINICA Informationis (in Chinese) 2023.

Related Experiments

     Competitions (selected)

  • MICCAI 2022 - Glaucoma Oct Analysis and Layer Segmentation. Rank 5/100
  • CVPR 2022 Workshop FGVC9 Competition - Sorghum Cultivars 2022. Rank 4/253