研究主线
长期围绕可靠视觉智能展开，核心问题是：如何在噪声标签、弱标注、长尾分布、跨域数据、低质量图像和开放环境等不可靠条件下，学习可靠、可解释、可泛化的视觉与多模态知识。相关研究覆盖鲁棒机器学习、多模态视觉理解、医学影像分析等方向。
研究方向
1. 可靠机器学习与开放环境学习：面向噪声标签、弱标注、长尾分布、异常样本、跨域数据和开放环境等复杂数据条件，研究可靠样本筛选、标签纠正、开放集识别、跨域泛化和模型可信评测方法。
2. 多模态视觉理解与行业智能体应用：研究视觉-语言模型调优与评测、跨模态语义对齐、智能体记忆机制与评测，并面向知识文档、文档生成、图像编辑等场景开展应用探索。
3. 医学影像分析：围绕医学图像分割、疾病识别，研究低成本标注和复杂退化条件下的可靠建模方法。
代表性论文（Google Scholar: https://scholar.google.com/citations?user=Hrm9cdMAAAAJ&hl=en）
[22] De Cheng, Yubo Li, Chaowei Fang, Shizhou Zhang, Nannan Wang, Xinbo Gao. Isolating Interference Factors for Robust Cloth-Changing Person Re-Identification. TPAMI, 2026.
[21] Chaowei Fang, Bolin Fu, De Cheng, Chengpei Tang, Guanbin Li. Learning Prompt Adapters for Forgetting-Free Continual Image Super-resolution. TIP, 2026.
[20] Chaowei Fang, Bolin Fu, Tao Yang, De Cheng. Improving face forgery detection via hierarchical mixture of experts and fine-grained visual-text alignment. PR, 2026.
[19] Ziyou Xiang, Chaowei Fang, Zhihong Wu, Jiliang Li, Di Xu, De Cheng. TriPrompt: Progressive Local Prompting for Few-shot Out-of-Distribution Detection. NeurIPS, 2026.
[18] Zhuoyue Zhang, Yiding Sun, Chaowei Fang, Haozhe Cheng, Jian Liu, Jihua Zhu, Ajmal Saeed Mian. Diffusion Masked Pretraining for Dynamic Point Cloud. NeurIPS, 2026.
[17] Yiding Sun, Dongxu Zhang, Jihua Zhu, Haozhe Cheng, Zhengqiao Li, Pengcheng Li, Chaowei Fang, Yonghao Dong, Lin Chen. Tri-Efficient Transfer Learning for Point Cloud Videos. ECCV, 2026.
[16] Junye Chen, Chaowei Fang, Jichang Li, Yicheng Leng, Guanbin Li. Decouple and Couple: Exploiting Prior Knowledge for Visible Video Watermark Removal. TIP, 2025.
[15] Chaowei Fang, Bolin Fu, De Cheng, Lechao Cheng, Guanbin Li. Dual-domain Adaptation Networks for Realistic Image Super-resolution. TMM, 2025.
[14] Chaowei Fang, Bolin Fu, De Cheng, Lechao Cheng, Dingwen Zhang. High-frequency structure transformer for magnetic resonance image super-resolution. PR, 2025.
[13] Zihao Mo, Junye Chen, Chaowei Fang, Guanbin Li. PatchWiper: Leveraging Dynamic Patch-Wise Parameters for Real-World Visible Watermark Removal. ACM MM, 2025.
[12] Yicheng Leng, Chaowei Fang, Junye Chen, Yixiang Fang, Sheng Li, Guanbin Li. Bridging Knowledge Gap between Image Inpainting and Large-Area Visible Watermark Removal. AAAI, 2025.
[11] Chaowei Fang, Hangfei Ma, Zhihao Li, De Cheng, Yue Zhang, Guanbin Li. Screening, Rectifying, and Re-Screening: A Unified Framework for Tuning Vision-Language Models with Noisy Labels. IJCAI, 2025.
[10] Guanbin Li, Zhuohua Chen, Mingzhi Mao, Liang Lin, Chaowei Fang. Uncertainty-aware Active Domain Adaptive Salient Object Detection. TIP, 2024.
[9] Ying Yang, De Cheng, Chaowei Fang, Yubiao Wang, Changzhe Jiao, Lechao Cheng, Nannan Wang, Xinbo Gao. Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection. NeurIPS, 2024.
[8] Chaowei Fang, Qian Wang, Lechao Cheng, Zhifan Gao, Chengwei Pan, Zhen Cao, Zhaohui Zheng, Dingwen Zhang. Reliable Mutual Distillation for Medical Image Segmentation under Imperfect Annotations. TMI, 2023.
[7] Weizhi Zhong, Chaowei Fang, Yinqi Cai, Pengxu Wei, Gangming Zhao, Liang Lin, Guanbin Li. Identity-Preserving Talking Face Generation with Landmark and Appearance Priors. CVPR, 2023.
[6] Yuxiang Nie, Chaowei Fang, Lechao Cheng, Liang Lin, Guanbin Li. Adapting Object Size Variance and Class Imbalance for Semi-Supervised Object Detection. AAAI, 2023.
[5] Junkai Huang, Chaowei Fang, Weikai Chen, Zhenhua Chai, Xiaolin Wei, Pengxu Wei, Liang Lin, Guanbin Li. Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning. ICCV, 2021.
[4] Feida Zhu, Chaowei Fang, Kai-Kuang Ma. PNEN: Pyramid Non-Local Enhanced Networks. TIP, 2020.
[3] Chaowei Fang, Guanbin Li, Xiaoguang Han, Yizhou Yu. Self-Enhanced Convolutional Network for Facial Video Hallucination. TIP, 2019.
[2] Chaowei Fang, Guanbin Li, Chengwei Pan, Yiming Li, Yizhou Yu. Globally Guided Progressive Fusion Network for 3D Pancreas Segmentation. MICCAI, 2019.
[1] Chaowei Fang, Zicheng Liao, Yizhou Yu. Piecewise Flat Embedding for Image Segmentation. TPAMI, 2019.
项目与研究基础
项目基础：主持国家自然科学基金面上项目、国家自然科学基金青年项目、华为昇腾创新模型开发等科研项目，具备从问题定义、技术路线设计、算法研发到实验验证和成果凝练的完整经验。
研究积累：在医学影像、鲁棒学习、图像恢复、多模态理解和开放环境识别等方向形成了较系统的研究积累，可支持学术研究、横向合作和应用原型开发。
面向合作
欢迎企业、医院、科研院所、政府部门、兄弟高校和产业伙伴围绕可靠视觉智能、多模态AI、医学影像分析和行业智能体应用等方向开展合作交流。
邮箱：chaoweifang AT outlook.com