个人简介

rabey雷竞技-计算机科学与技术学院副教授，硕士生导师，博士，湖北省楚天学者，ACM武汉新星。2016年6月于南开大学-软件学院获得学士学位，2022年1月于北京大学-信息科学与技术学院获博士学位，2019年9月-2020年9月赴美国卡内基梅隆大学（CMU）访学。作为项目负责人主持国家自然科学基金1项，在NeurIPS、ICML、CVPR、AAAI、ACM MM、WWW、IJCAI、TKDE、TIP等国际权威会议、期刊发表论文50余篇，其中以第一作者或通讯作者身份发表CCF-A类论文27篇，一区SCI期刊3篇，获评2022年ACM北京分会优博（北京共2人），2023年湖北省科技进步一等奖。目前主要从事多模态大模型、小样本学习、迁移学习、计算机视觉、可解释性机器学习等方面的研究工作。

社会兼职

CCF-YOCSEF武汉-候任主席

教学课程

课程：Python人工智能实践（本科）；数据挖掘（研究生）；数据挖掘高级专题（研究生）
成果：rabey雷竞技2023-2024学年教师教学竞赛二等奖
课程建设：rabey雷竞技2024年本科人工智能课程建设项目；rabey雷竞技人工智能教育教学研究中心委员

研究领域

多模态大模型、小样本学习、迁移学习、计算机视觉、可解释性机器学习

研究课题

1. 面向开放世界的模块化终生学习方法研究（国家自然科学基金）（2023-2025）（主持）
2. 高可信联邦图学习基础理论与方法研究（国家自然科学基金）（2024-2027）（参与）

专利&软件著作权

1. José M. F. Moura, Yixiong Zou, Shanghang Zhang, Guangyao Chen, Yonghong Tian. FEW SHOT ACTION RECOGNITION IN UNTRIMMED VIDEOS (US Patent App. 17/529,011), App Date: 2022.5.26
2. 田永鸿，邹逸雄，史业民，王耀威. 一种小样本视频识别方法（专利号：ZL201810184700.9）. 授权日：2020.7.10
3. 王耀威，李诗文，田永鸿，邹逸雄，曾炜. 基于深度学习的车牌检测与识别方法和装置（申请号：201810600935.1），申请日：2018.6.12
4. 苏莉，邹逸雄，姚敦洁，张婉君，周鑫红，吴瑞哲，王养怡，吴秋晗，周鑫炜. 一种乳腺癌细胞类群鉴定、以及转移或耐药亚型肿瘤细胞特征识别方法及系统（申请号：2024109668731）. 申请日：2024.7.18

学术论文

 代表性论文（按时间顺序）：
     1. Yang Qiu, Yixiong Zou (通讯), et al; Rethinking Graph Generalization through the Lens of Sharpness-Aware Minimization, The ACM Web Conference 2026 (WWW 2026, CCF-A类论文), April 13th – 17th, 2026, Dubai, United Arab Emirates
     2. Qingyang Yan, Guangyao Chen, Yixiong Zou (通讯), et al; Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding, Annual AAAI Conference on Artificial Intelligence (AAAI 2026, Oral, CCF-A类论文), Jan 20th – Jan 27th, 2026, Singapore
     3. Zhenyu Zhang, Guangyao Chen, Yixiong Zou (通讯), et al; Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning, Annual AAAI Conference on Artificial Intelligence (AAAI 2026, CCF-A类论文), Jan 20th – Jan 27th, 2026, Singapore
     4. Jintao Tong, Wenwei Jin, Pengda Qin, Anqi Li, Yixiong Zou (通讯), et al; FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models, Annual Conference on Neural Information Processing Systems (NeurIPS 2025, CCF-A类论文), Nov 30th – Dec 7th, 2025, San Diego, CA, USA
     5. Yang Qiu, Yixiong Zou (通讯), et al; Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization, Annual Conference on Neural Information Processing Systems (NeurIPS 2025, CCF-A类论文), Nov 30th – Dec 7th, 2025, San Diego, CA, USA
     6. Yongwei Jiang, Yixiong Zou (通讯), et al; Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning, International Conference on Computer Vision (ICCV 2025, CCF-A类论文), Oct 19–23th, 2025, Honolulu, Hawai'i
     7. Zechao Hu, Zhengwei Yang, Hao Li, Zheng Wang, Yixiong Zou (通讯), et al; Cross-Category Subjectivity Generalization for Style-Adaptive Sketch Re-ID, International Conference on Computer Vision (ICCV 2025, CCF-A类论文), Oct 19–23th, 2025, Honolulu, Hawai'i
     8. Shuai Yi, Yixiong Zou (通讯), et al; Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning, International Conference on Machine Learning (ICML 2025, Spotlight, CCF-A类论文), Vancouver, CA, 2025-7-13 - 2025-7-19
     9. Shuai Yi, Yixiong Zou (通讯), et al; Random Registers for Cross-Domain Few-Shot Learning, International Conference on Machine Learning (ICML 2025, CCF-A类论文), Vancouver, CA, 2025-7-13 - 2025-7-19
     10. Jintao Tong, Ran Ma, Yixiong Zou (通讯), et al; Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation, International Conference on Machine Learning (ICML 2025, Spotlight, CCF-A类论文), Vancouver, CA, 2025-7-13 - 2025-7-19
     11. Jintao Tong, Yixiong Zou (通讯), et al; Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation, International Conference on Machine Learning (ICML 2025, CCF-A类论文), Vancouver, CA, 2025-7-13 - 2025-7-19
     12. Yuhan Liu, Yixiong Zou (通讯), et al; The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025, CCF-A类论文), Nashville, USA, 2025-6-11 - 2025-6-15
     13. Ran Ma, Yixiong Zou (通讯), et al; Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning, Annual AAAI Conference on Artificial Intelligence (AAAI 2025, CCF-A类论文), Philadelphia, USA, 2025-2-25 - 2025-3-4
     14. Yixiong Zou, et al; A Closer Look at the CLS Token for Cross-Domain Few-Shot Learning, Annual Conference on Neural Information Processing Systems (NeurIPS 2024, CCF-A类论文), Vancouver, CA, 2024-12-10 - 2024-12-15
     15. Yixiong Zou, et al; Attention Temperature Matters in ViT-Based Cross-Domain Few-Shot Learning, Annual Conference on Neural Information Processing Systems (NeurIPS 2024, CCF-A类论文), Vancouver, CA, 2024-12-10 - 2024-12-15
     16. Yiman Hu, Yixiong Zou (通讯), et al; Generate Universal Adversarial Perturbations for Few-Shot Learning, Annual Conference on Neural Information Processing Systems (NeurIPS 2024, CCF-A类论文), Vancouver, CA, 2024-12-10 - 2024-12-15
     17. Jintao Tong, Yixiong Zou (通讯), et al; Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation, Annual Conference on Neural Information Processing Systems (NeurIPS 2024, CCF-A类论文), Vancouver, CA, 2024-12-10 - 2024-12-15
     18. Yixiong Zou, et al; Compositional Few-Shot Class-Incremental Learning. International Conference on Machine Learning (ICML 2024, CCF-A类论文), Vienna, Austria, July 21-27, 2024
     19. Yixiong Zou, et al; Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024, CCF-A类论文), Seattle, USA, June 17-21, 2024
     20. Haichen Zhou, Yixiong Zou (通讯), et al; Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning. International Joint Conference on Artificial Intelligence (IJCAI 2024, CCF-A类论文), Jeju Island, South Korea, August 3-9, 2024.
     21. Jie Han, Yixiong Zou (通讯), et al; Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling. Annual AAAI Conference on Artificial Intelligence (AAAI 2024, CCF-A类论文), Vancouver, Canada, February 20th-27th, 2024.
     22. Zhenyu Zhang, Guangyao Chen, Yixiong Zou (通讯), et al; Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-shot Open-Set Recognition. ACM International Conference on Multimedia (ACM MM 2024, CCF-A类论文), Melbourne, Australia, Oct 28 - Nov 1, 2024.
     23. Zhenyu Zhang, Guangyao Chen, Yixiong Zou (通讯), et al; MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning. ACM International Conference on Multimedia (ACM MM 2024, Oral, CCF-A类论文), Melbourne, Australia, Oct 28 - Nov 1, 2024.
     24. Yixiong Zou, et al; Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation, Annual Conference on Neural Information Processing Systems (NeurIPS 2022, CCF-A类论文), New Orleans, LA, USA, 2022-11-28 - 2022-12-3
     25. Yixiong Zou, et al; Revisiting Mid-Level Patterns for Cross-Domain Few-Shot Recognition, ACM International Conference on Multimedia (ACM MM 2021, CCF-A类论文), Chengdu, China, 2021-10-20 - 2021-10-24
     26. Yixiong Zou, et al; Annotation-Efficient Untrimmed Video Action Recognition, ACM International Conference on Multimedia (ACM MM 2021, CCF-A类论文, Chengdu, China, 2021-10-20 - 2021-10-24
     27. Yixiong Zou, et al; Compositional Few-Shot Recognition with Primitive Discovery and Enhancing, ACM International Conference on Multimedia (ACM MM 2020, Oral, CCF-A类论文), Seattle, WA, USA, 2020-10-12 - 2020-10-16
     28. Yiman Hu, Yixiong Zou (通讯), et al; Alleviating Noise Memorization for Adversarially Robust Few-Shot Learning, Neural Networks (CCF-B类论文, 一区SCI期刊), 2026
     29. Yicong Liu, Yixiong Zou (通讯), et al; Spectral Decomposition and Transformation for Cross-Domain Few-Shot Learning, Neural Networks (CCF-B类论文, 一区SCI期刊), 2024, https://doi.org/10.1016/j. neunet.2024.106536
     30. Yixiong Zou, et al; Adaptation-Oriented Feature Projection for One-shot Action Recognition, IEEE Transactions on Multimedia (TMM 2020, CCF-B类论文, 一区SCI期刊), 2020, 22(12): 3166-3179

其他论文:
     请见 https://scholar.google.com/citations?user=VXxF0mcAAAAJ&hl=zh-CN

竞赛获奖:
     2025年CVPR Workshop NTIRE-CDFSOD Challenge（跨域小样本目标检测竞赛）- 全球第三名（唯一指导老师）
     2023年第五届全球校园人工智能算法精英大赛 - AIGC驱动的小样本分类 - 全国一等奖（唯一指导老师）

   

专业活动