Qi Wei (魏琦)
Thanks to all my collaborators for your invaluable support and expertise in these researches.
(† indicates equal contribution)
Preprint
-
Qi Wei, Lei Feng, Haobo Wang, Bo An.
Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labels.
[Paper]
[Code]
-
Yuwei Nie, Shuo He, Qi Wei, Feng Liu, Lei Feng.
BDetCLIP: Multimodal Prompting Contrastive Test-Time Backdoor Detection.
[Paper]
Accepted
-
Qi Wei, Shuo He, Jiahan Zhang, Lei Feng, Bo An.
Influence-Based Fair Selection for Sample-Discriminative Backdoor Attack.
Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence (AAAI) 2025.
[Paper]
[Appdx]
[Poster]
[Code]
(Oral, Acceptance Rate: ~4.6%, 600/12,957)
-
Haoliang Sun†, Qi Wei†, Lei Feng, Yupeng Hu, Fan Liu, Hehe Fan, Yilong Yin.
Variational Rectification Inference for Learning with Noisy Labels.
International Journal of Computer Vision (IJCV), 2025, vol. 133, pp. 652–671.
[Paper]
[Code]
-
Jiahan Zhang†, Qi Wei†, Feng Liu, Lei Feng.
Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data.
Proceedings of the 41st International Conference on Machine Learning (ICML) 2024, pp. 60004-60020.
[Paper]
[Code]
(Oral, Acceptance Rate: ~1.5%, 144/9,473)
-
Hong You, Xian Zhong, Wenxuan Liu, Qi Wei, Wenxin Huang, Zhaofei Yu, Tiejun Huang.
Converting Artificial Neural Networks to Ultra-Low-Latency Spiking Neural Networks for Action Recognition.
IEEE Transactions on Cognitive and Developmental Systems (TCDS), 2024
[Paper]
-
Qi Wei, Lei Feng, Haoliang Sun, Ren Wang, Rundong He, Yilong Yin.
Learning Sample-Aware Threshold for Semi-Supervised Learning.
Machine Learning (MLJ) 2024, vol. 113, pp. 5423–5445.
[Paper]
[Poster]
-
Qi Wei, Lei Feng, Haoliang Sun, Chenhui Guo, Ren Wang, Yilong Yin.
Fine-Grained Classification with Noisy Labels.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, pp. 11651-11660.
[Paper]
[Appdx]
[Poster]
[Code]
-
Qi Wei, Haoliang Sun, Xiankai Lu, Yilong Yin.
Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization.
Proceedings of the European Conference on Computer Vision (ECCV) 2022, pp. 516-532.
[Paper]
[Appdx]
[Poster]
[Code]
-
Haoliang Sun†, Chenhui Guo†, Qi Wei, Zhongyi Han, Yilong Yin.
Learning to Rectify for Robust Learning with Noisy Labels.
Pattern Recognition (PR) 2022, vol. 124, 108467.
[Paper]
[Code]
-
魏琦, 孙皓亮, 马玉玲, 尹义龙. 面向标签噪声的联合训练框架.
中国科学-信息科学 2023
[Paper]
[Code]
|