Yibo Zhou (周亦博)

Ph.D. in Artificial Intelligence

Beihang University, 2026

Beijing, China

ybzhou@buaa.edu.cn

I am Yibo Zhou, a researcher working on Computer Vision and Trustworthy Machine Learning. I received my Ph.D. in Artificial Intelligence from Beihang University in June 2026. My research focuses on developing reliable machine learning systems that can learn from imbalanced data, mitigate spurious correlations, and generalize robustly under distribution shifts. My research has appeared in leading computer vision and machine learning venues, including IEEE TPAMI, IJCV, ICML, IJCAI, and CVPR.

🎓 Academic Journey

Beihang University

Ph.D. in Artificial Intelligence

September 2022 – June 2026

Degree awarded in June 2026 · Beijing, China

University of California San Diego

M.S. in Electrical Engineering

August 2017 – May 2019

San Diego, California, USA

Lanzhou University

B.S. in Materials Physics

August 2013 – June 2017

Lanzhou, China

💼 Professional Experience

OPPO Guangdong Mobile Telecommunications Corp., Ltd.

Artificial Intelligence Algorithm Engineer

101 Laboratory · Imaging Algorithm Development Department

July 2019 – March 2021 · Shenzhen, China

selected publications

ICML

Is Spurious Correlation Removal Always Learnable?

Yibo Zhou, Bo Li, Hai-Miao Hu, Hanzi Wang, Xiaokang Zhang, and Ruifan Zhang

In International Conference on Machine Learning, 2026

Accepted at ICML 2026

arXiv Bib

@inproceedings{zhou2026spurious,
  author = {Zhou, Yibo and Li, Bo and Hu, Hai-Miao and Wang, Hanzi and Zhang, Xiaokang and Zhang, Ruifan},
  title = {Is Spurious Correlation Removal Always Learnable?},
  booktitle = {International Conference on Machine Learning},
  year = {2026},
  note = {Accepted at ICML 2026},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/2606.12930},
}

TPAMI

Heterogeneous Feature Re-Sampling for Balanced Pedestrian Attribute Recognition

Yibo Zhou, Bo Li, Hai-Miao Hu, Xiaokang Zhang, Dongping Zhang, and Hanzi Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

DOI Bib

@article{zhou2025heterogeneous,
  author = {Zhou, Yibo and Li, Bo and Hu, Hai-Miao and Zhang, Xiaokang and Zhang, Dongping and Wang, Hanzi},
  title = {Heterogeneous Feature Re-Sampling for Balanced Pedestrian Attribute Recognition},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume = {47},
  number = {4},
  pages = {2706--2722},
  year = {2025},
  doi = {10.1109/TPAMI.2025.3526930},
  url = {https://doi.org/10.1109/TPAMI.2025.3526930},
}

IJCV

A Solution to Co-occurrence Bias in Pedestrian Attribute Recognition: Theory, Algorithms, and Improvements

Yibo Zhou, Hai-Miao Hu, Jinzuo Yu, Haotian Wu, Shiliang Pu, and Hanzi Wang

International Journal of Computer Vision, 2025

DOI Bib

@article{zhou2025cooccurrence,
  author = {Zhou, Yibo and Hu, Hai-Miao and Yu, Jinzuo and Wu, Haotian and Pu, Shiliang and Wang, Hanzi},
  title = {A Solution to Co-occurrence Bias in Pedestrian Attribute Recognition: Theory, Algorithms, and Improvements},
  journal = {International Journal of Computer Vision},
  volume = {133},
  number = {7},
  pages = {4712--4726},
  year = {2025},
  doi = {10.1007/s11263-025-02405-7},
  url = {https://doi.org/10.1007/s11263-025-02405-7},
}

ICML

Pedestrian Attribute Recognition as Label-Balanced Multi-Label Learning

Yibo Zhou, Hai-Miao Hu, Yirong Xiang, Xiaokang Zhang, and Haotian Wu

In Proceedings of the 41st International Conference on Machine Learning, Jul 2024

Bib PDF

@inproceedings{pmlr-v235-zhou24j,
  title = {Pedestrian Attribute Recognition as Label-Balanced Multi-Label Learning},
  author = {Zhou, Yibo and Hu, Hai-Miao and Xiang, Yirong and Zhang, Xiaokang and Wu, Haotian},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning},
  pages = {61964--61978},
  year = {2024},
  editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix},
  volume = {235},
  series = {Proceedings of Machine Learning Research},
  month = jul,
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v235/zhou24j.html},
}

IJCAI

A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition

Yibo Zhou, Hai-Miao Hu, Jinzuo Yu, Zhenbo Xu, Weiqing Lu, and Yuran Cao

In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, Aug 2023

Main Track

DOI Bib

@inproceedings{ijcai2023p203,
  title = {A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition},
  author = {Zhou, Yibo and Hu, Hai-Miao and Yu, Jinzuo and Xu, Zhenbo and Lu, Weiqing and Cao, Yuran},
  booktitle = {Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor = {Elkind, Edith},
  pages = {1831--1839},
  year = {2023},
  month = aug,
  note = {Main Track},
  doi = {10.24963/ijcai.2023/203},
  url = {https://doi.org/10.24963/ijcai.2023/203},
}

CVPR

Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection

Yibo Zhou

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

DOI Bib

@inproceedings{zhou2022rethinking,
  author = {Zhou, Yibo},
  title = {Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {7379--7387},
  year = {2022},
  doi = {10.1109/CVPR52688.2022.00723},
  url = {https://doi.org/10.1109/CVPR52688.2022.00723},
}