Postdoctoral Researcher [Google Scholar] [Github] Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation Chinese Academy of Sciences 3/F, 17W, Science Park West Avenue, Hong Kong Science Park, Hong Kong. Email: zhufei2018 AT ia DOT ac DOT cn

About me

I am currently a postdoctoral researcher at the Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences. I am fortunate to work with Prof. Zhaoxiang Zhang. I received my Ph.D. in Pattern Recognition and Intelligent Systems from the Institute of Automation, Chinese Academy of Sciences, where I was fortunate to be advised by Prof. Cheng-Lin Liu and Prof. Xu-Yao Zhang. Prior to this, I received the B.E. degree from Tsinghua University.

Research Highlights: My research interests include topics in reliability (e.g., confidence estimation, failure detection) and adaptability (e.g., continual learning, novel class discovery) of mechine learning models, especially in the open world/environment applications.
I am open to discussion or collaboration. Feel free to contact me if you are interested.

Preprints

• Federated Class-Incremental Learning with Prototype Guided Transformer.
  Haiyang Guo, Fei Zhu, Wenzhuo Liu, Xu-Yao Zhang, Cheng-Lin Liu.
  ArXiv 2024 [paper].
  

• Towards trustworthy dataset distillation.
  Shijie Ma, Fei Zhu, Zhen Cheng, Xu-Yao Zhang.
  ArXiv 2023 [paper].
  

• Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection.
  Zhen Cheng, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu.
  ArXiv 2023 [paper].
  

Selected Publications

• RCL: Reliable Continual Learning for Unified Failure Detection.
  Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu, Zhaoxiang Zhang.
  CVPR 2024 [paper] [arxiv] [code].
  

• Active Generalized Category Discovery.
  Shijie Ma, Fei Zhu, Zhun Zhong, Xu-Yao Zhang, Cheng-Lin Liu.
  CVPR 2024 [paper] [arxiv] [code].
  

• Revisiting Confidence Estimation: Towards Reliable Failure Prediction.
  Fei Zhu, Xu-Yao Zhang, Zhen Cheng, Cheng-Lin Liu.
  TPAMI 2024 [paper] [arxiv] [code].
  

• Learning by Seeing More Classes.
  Fei Zhu, Xu-Yao Zhang, Rui-Qi Wang, Cheng-Lin Liu.
  TPAMI 2023 [paper].
  

• Imitating the Oracle: Towards Calibrated Model for Class Incremental Learning.
  Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu.
  Neural Networks 2023 [paper] [code].
  

• OpenMix: Exploring Outlier Samples for Misclassification Detection.
  Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu.
  CVPR 2023 Highlight Paper (Top 2.5%) [paper] [arxiv] [code].
  

• Rethinking Confidence Calibration for Failure Prediction.
  Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu.
  ECCV 2022 [paper] [arxiv] [code].
  

• Prototype Augmentation and Self-Supervision for Incremental Learning.
  Fei Zhu, Xu-Yao Zhang, Chuang Wang, Fei Yin, Cheng-Lin Liu.
  CVPR 2021 Oral Paper (Top 4%) [paper] [code].
  

• Class-Incremental Learning via Dual Augmentation.
  Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu.
  NeurIPS 2021 [paper] [code].
  

• Class Incremental Learning: A Review and Performance Evaluation (In Chinese).
  Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu.
  Acta Automatica Sinica 2023, invited reviews [paper].
  

• Adversarial Training with Distribution Normalization and Margin Balance.
  Zhen Cheng, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu.
  Pattern Recognition 2023 [paper].
  

• Decoding lip language using triboelectric sensors with deep learning.
  Yi-Jia Lu*, Han Tan*, Jia Cheng*, Fei Zhu, Bing Liu, Shan-Shan Wei, LinHong Ji, Zhong-Lin Wang.
  Nature Communications 2022 Highlight Paper [paper].
  

Academic Services

• Conference Reviewer: NeurIPS, ICLR, CVPR, ICCV, ECCV, AAAI, IJCAI

• Journal Reviewer: IEEE TIP, TNNLS, PR, NN, IJCV