Qi Fan (范琦)   Associate Professor (准聘副教授) R&L Group School of Intelligence Science and Technology State Key Laboratory for Novel Software Technology Nanjing University, Suzhou Campus Email: fanqi@nju.edu.cn; fanqics@gmail.com [Google Scholar]

Biography

Currently I am a Tenure-Track Associate Professor of School of Intelligence Science and Technology in Nanjing University.
I am also a member of R&L Group, led by professor Yang Gao.

I received my B.Eng. degree in School of Electrical Engineering in June 2015 from China University of Mining and Technology.
I received my Master degree in Department of Automation in June 2018 from Tsinghua University.
I received my Ph.D. degree in Department of Computer Science & Engineering in October 2023 from The Hong Kong University of Science and Technology under the supervision of Prof. Chi-Keung TANG (IEEE Fellow) and Prof. Yu-Wing TAI.

Research Interests

Research interests include computer vision and machine learning.
My research primarily explores visual perception generalization technologies under data or resource constraints, including few-shot learning (detection, segmentation, classification, etc.), and the efficient fine-tuning of foundational visual models.

Positions

• 请想要申请读研/读博的同学首先读这个文档: [招生要求与学生培养]

• 招收 2026 级考研的硕士研究生 1 人，欢迎与我联系！

• 招收 2026 级申请-考核制博士 1 人，欢迎与我联系！

• 常年招收硕士研究生和博士研究生、科研助理、科研实习生等，欢迎与我联系！

• 招收 2026 级保研/推免的硕士研究生 2 人，直博生 1 人，欢迎与我联系！（已招满）

• 招收 2025 级申请-考核制的博士研究生 2 人，欢迎与我联系！（已招满）

• 招收 2025 级保研/推免的硕士研究生 3 人，欢迎与我联系！（已招满）

• 招收 2024 级考研的硕士研究生 2 人，欢迎与我联系！（已招满）

Preprints

• Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation [paper]
  
  Xunzhi Xiang, Yabo Chen, Guiyu Zhang, Zhongyu Wang, Zhe Gao, Quanming Xiang, Gonghu Shang, Junqi Liu, Haibin Huang, Yang Gao, Chi Zhang, Qi Fan (Corresponding Author), Xuelong Li
  
  arXiv preprint arXiv:2508.03334
  
• Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation [paper]
  
  Xunzhi Xiang, Qi Fan (Corresponding Author)
  
  arXiv preprint arXiv:2506.18226
  
• Training-Free Open-Vocabulary Semantic Segmentation with Context Pyramid Refinement [Under Review]
  
  Jialei Chen, Qi Fan (Corresponding Author), Zhenzhen Quan, Dongyue Li, Xu Zheng, Hiroshi Murase, Daisuke Deguchi
  
  In Submission, 2025
  
• Retain and Adapt: Auto-Balanced Model Editing for Open-Vocabulary Object Detection under Domain Shifts [Under Review]
  
  Zixuan Duan, Fengyuan Lu, Xunzhi Xiang, Wenbin Li, Qi Fan (Corresponding Author), Yang Gao
  
  In Submission, 2025
  
• QPrompt-R1: Real-Time Reasoning for Domain Generalized Semantic Segmentation via Group-Relative Query Alignment [Under Review]
  
  Fengyuan Lu, Zixuan Duan, Xunzhi Xiang, Zhicheng Zhang, Wenbin Li, Qi Fan (Corresponding Author), Yang Gao
  
  In Submission, 2025
  
• HERA: Efficient Test-Time Adaptation for Cross-Domain Few-Shot Segmentation with Vision Foundation Models [Under Review]
  
  Junyuan Ma, Xunzhi Xiang, Wenbin Li, Qi Fan (Corresponding Author), Yang Gao
  
  In Submission, 2025
  
• SmartSAM: Segment Ambiguous Objects like Smart Annotators [Under Review]
  
  Zhe Gao, Shiyu Shen, Xunzhi Xiang, Wenbin Li, Qi Fan (Corresponding Author), Yang Gao
  
  In Submission, 2025
  

Publications

• Semantic-Centric Alignment for Zero-shot Panoptic Segmentation with Limited Data [Accepted]
  
  Jialei Chen, Daisuke Deguchi, Dongyue Li, Xu Zheng, Seigo Ito, Hiroshi Murase, Qi Fan (Corresponding Author)
  
  International Journal of Computer Vision (IJCV) , 2025
  
• DON'T NEED RETRAINING: A Mixture of DETR and Vision Foundation Models for Cross-Domain Few-Shot Object Detection [Accepted]
  
  Changhan Liu, Xunzhi Xiang, Zixuan Duan, Wenbin Li, Qi Fan (Corresponding Author), Yang Gao
  
  Neural Information Processing Systems (NeurIPS) , 2025
  
• Adapting In-Domain Few-Shot Segmentation to New Domains without Retraining [paper]
  
  Qi Fan, Kai-Qi Liu, Nian Liu, Hisham Cholakkal, Rao Muhammad Anwer, Wenbin Li, Yang Gao
  
  International Conference on Computer Vision (ICCV) , 2025
  
• Robust Object Detection with Domain-Invariant Training and Continual Test-Time Adaptation [paper]
  
  Qi Fan, Mattia Segu, Bernt Schiele, Dengxin Dai, Yu-Wing Tai, Chi-Keung Tang
  
  International Journal of Computer Vision (IJCV) , 2025
  
• Stable Segment Anything Model [paper]
  
  Qi Fan, Xin Tao, Lei Ke, Mingqiao Ye, Yuan Zhang, Pengfei Wan, Yu-Wing Tai, Chi-Keung Tang
  
  International Conference on Learning Representations (ICLR) , 2025
  
• Domain-Rectifying Adapter for Cross-domain Few-Shot Segmentation [paper]
  
  Jiapeng Su, Qi Fan (Co-First Author), Guangming Lu, Fanglin Chen, Wenjie Pei
  
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2024
  
• FSODv2: A Deep Calibrated Few-Shot Object Detection Network [paper]
  
  Qi Fan, Wei Zhuo, Chi-Keung Tang, Yu-Wing Tai
  
  International Journal of Computer Vision (IJCV) , 2024 (CVPR2020 extension)
  
• Learning to Learn Better Visual Prompts [paper]
  
  Fengxiang Wang, Wanrong Huang, Shaowu Yang, Qi Fan, Long Lan
  
  Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2024
  
• GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector [paper]
  
  Peng Zheng, Huazhu Fu, Deng-Ping Fan, Qi Fan, Jie Qin, Yu-Wing Tai, Chi-Keung Tang, Luc Van Gool
  
  IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) , 2023 (CVPR2021 extension)
  
• Towards Robust Object Detection Invariant to Real-World Domain Shifts [paper]
  
  Qi Fan, Mattia Segu, Yu-Wing Tai, Fisher Yu, Chi-Keung Tang, Bernt Schiele, Dengxin Dai
  
  International Conference on Learning Representations (ICLR) , 2023
  
• Self-Support Few-Shot Semantic Segmentation [paper]
  
  Qi Fan, Wenjie Pei, Yu-Wing Tai, Chi-Keung Tang
  
  European Conference on Computer Vision (ECCV) , 2022
  
• Few-Shot Video Object Detection [paper]
  
  Qi Fan, Chi-Keung Tang, Yu-Wing Tai
  
  European Conference on Computer Vision (ECCV) , 2022
  
• Few-Shot Object Detection with Model Calibration [paper]
  
  Qi Fan, Chi-Keung Tang, Yu-Wing Tai
  
  European Conference on Computer Vision (ECCV) , 2022
  
• Group Collaborative Learning for Co-Salient Object Detection [paper]
  
  Qi Fan, Deng-Ping Fan, Huazhu Fu, Chi-Keung Tang, Ling Shao, Yu-Wing Tai
  
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2021
  
• Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation [paper]
  
  Qi Fan, Lei Ke, Wenjie Pei, Chi-Keung Tang, Yu-Wing Tai
  
  European Conference on Computer Vision (ECCV) , 2020
  
• Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector [paper]
  
  Qi Fan, Wei Zhuo, Chi-Keung Tang, Yu-Wing Tai
  
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2020
  

Awards and Honors

• 2024 ECCV 2nd workshop on Vision-based InduStrial InspectiON (VISION) Data Challenge - One Shot Industrial Defect Segmentation - 2nd place
• 2016 China Collegiate Computing Contest Big Data Challenge - Champion