About Me

Hi! I’m Feiran Li (李斐然, E-mail: lifeiran@iie.ac.cn). Now I am a PhD. student of Institute of Information Engineering, Chinese Academy of Sciences (IIE, CAS), supervised by Prof. Qingming Huang (黄庆明) (IEEE Fellow) and Qianqian Xu (许倩倩) (Professor at ICT, CAS). I have received the B.E. degree in computer science and technology from CUMT in 2023. My research interest includes computer vision (计算机视觉) and generative model (生成模型). I have authored or co-authored several academic papers in top-tier international conferences and journals, including ICML, ICCV, etc. If you are interested in my research, please email me at lifeiran@iie.ac.cn.

🔥 News

• 2026.03： 🎉🎉 One Paper has been accepted by CVPR 2026.
• 2025.07： 🎉🎉 Winning the first-prize of the ICCV’25 Competition (DataCV Challenge), with one paper accepted by ICCV 2025 DataCV workshop.
• 2025.06:  🎉🎉 One Paper has been accepted by T-PAMI.
• 2025.05:  🎉🎉 One Paper has been accepted by ICML 2025.
• 2024.05:  🎉🎉 One Paper has been accepted by ICML 2024.

📝 Publications

ICML 2024 (Spotlight)

Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

Feiran Li, Qianqian Xu, Shilong Bao, Zhiyong Yang, Runmin Cong, Xiaochun Cao, Qingming Huang. International Conference on Machine Learning (ICML) 2024. (Spotlight, 3.5%) | [code] | [slides]

Project

• A generic approach to address the size-invariance problem in multi-object salient object detection.

ICML 2025

One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework for Diffusion Models

Feiran Li, Qianqian Xu, Shilong Bao, Zhiyong Yang, Xiaochun Cao, Qingming Huang. International Conference on Machine Learning (ICML) 2025. (26.9%) | [code]

• A text-image collaborative erasing framework for diffusion models.

CVPR 2026

BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation

Feiran Li, Qianqian Xu, Shilong Bao, Zhiyong Yang, Xilin Zhao, Xiaochun Cao, Qingming Huang. Conference on Computer Vision and Pattern Recognition (CVPR) 2026. (25.42%) | [code]

• A VLM&LLM-based black-box detection framework for text-image model backdoors.

TPAMI 2025

Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach

Shilong Bao, Qianqian Xu, Feiran Li, Zhiyong Yang, Boyu Han, Xiaochun Cao, Qingming Huang. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) 2025.| [code] | [slides]

Project

• Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation. Feiran Li, Qianqian Xu, Shilong Bao, Boyu Han, Zhiyong Yang, Qingming Huang. ICCV 2025 Workshop (Oral). [code].

• MOL: Joint Estimation of Micro-Expression, Optical Flow, and Landmark via Transformer-Graph-Style Convolution. Zhiwen Shao, Yifan Cheng, Feiran Li, Yong Zhou, Xuequan Lu, Yuan Xie, Lizhuang Ma. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), (Accepted).

• Joint Facial Action Unit Recognition and Self-supervised Optical Flow Estimation. Zhiwen Shao, Yong Zhou, Feiran Li, Hancheng Zhu, Bing Liu. Pattern Recognition Letters, 2024.

• Identity-invariant Representation and Transformer-style Relation for Micro-expression Recognition. Zhiwen Shao, Feiran Li, Yong Zhou, Hao Chen, Hancheng Zhu, Rui Yao. Applied Intelligence, 2023.

🎖 Honors and Awards

• 2021.12 2020-2021 National Scholarship for Undergraduates.
• 2020.12 2019-2020 National Scholarship for Undergraduates.

📖 Educations

2023.09 - now, Ph.D. Student.

Institute of Information Engineering, Chinese Academy of Sciences (IIE, CAS).

University of Chinese Academy of Sciences, Beijing.

2019.06 - 2023.06, Undergraduate.

School of Computer Science and Technology.

China University of Mining and Technology (CUMT), Xuzhou.