曹相湧 副教授 博士生导师
计算机科学与技术学院
跨媒体知识融合与工程应用研究所
陕西省大数据知识工程实验室
[Google Scholar] [Github]
Email: caoxiangyong@mail.xjtu.edu.cn
//caoxiangyong45@gmail.com
办公室:西一楼129(兴庆校区)
鸿理楼6106(创新港校区)
对机器学习和计算机视觉感兴趣的本科生、研究生、博士生,欢迎联系!
欢迎本科生联系科研训练,每年招收(学/专)硕士4名,博士1名,欢迎联系!
今年保研名额已满,明年博士名额已满!
博士 :芮翔宇(协孟老师)、王启舟(协孟老师)、刘佩、孙冬伟、李开宇、张必慧
研二: 庞立 、吴萱、尹攀、唐大涛、首云涛
研一:王洪中、张子涵、王文振、杨宇航
研零:陈佳亿、付婧
本科:温浩东(清华叉院,直博)、杜博东(港科直博)、鲍亚婕(南大直博)、马逸宁、崔龙(上交和上海AI Lab联培博士)、刘睿勋、曹晋、袁行健、宋佳怡、戴早、李佳霖
本科生去向:祝泽宇(NUS, 直博,发表一作CVPR)、黄俊豪(复旦和上海 AI Lab联合培养博士)、王一凡(上交和上海AI Lab联合培养博士,发表一作RS)
简介
副教授、博士生导师,哥伦比亚大学访问学者,主要从事机器学习、计算机视觉、底层图像处理、遥感图像解译、生成式大模型等方向研究。已在IJCV, SIAM J. Image Sciences, TIP, CVPR, ICCV等国际顶级期刊和会议发表论文60余篇,其中IEEE Trans. 29篇,以第一作者或通讯作者发表CCF A类期刊会议或中科院一区期刊26篇,一作或通讯ESI高被引论文5篇,谷歌引用次数2600余次,H-index 25, 申请国家发明专利10项,主持国家自然科学面上基金、青年基金、教育部考试院项目,作为骨干成员参与科技部重点研发、基金委重大、原创等项目,开发了首个多条件可控生成式遥感图像基础模型CRS-Diff,首个基于大模型的变化检测框架BAN, 首个多条件可控高光谱生成式基础模型HSIGene,开源首个最全面的遥感图像变化检测工具包OpenCD,研究成果获CVPR2024土地覆盖制图小样本挑战赛亚军,ISPRS多模态遥感应用算法智能解译大赛高光谱图像变化检测赛道季军,指导学生获美国大学生数学建模最高奖(O奖),研究成果落地于大唐华银、平高集团、比亚迪等公司,担任CVPR, ICCV, ECCV, ICLR, NeurIPS, UAI, TPAMI等顶级会议和期刊审稿人,担任IJCAI 2019高级程序委员会委员,PRCV 2023领域主席,Valse执行领域主席,CSIG青工委委员,CSIG遥感专委会委员, CSIG视觉传感专委会委员。
教育背景
2008.09-2012.06,西安交通大学数学与统计学院 信息与计算科学 理学学士
2012.09-2018.06,西安交通大学数学与统计学院 应用数学 理学博士 导师:徐宗本院士 孟德宇教授
2016.09-2017.09,哥伦比亚大学 电子工程系与数据科学中心联合培养博士 导师:John Paisley副教授
工作经历
2018.07-2021.12,西安交通大学数学与统计学院统计系,助理教授
2021.12-2022.03,西安交通大学电信学部计算机学院,助理教授
2022.04- 至 今, 西安交通大学电信学部计算机学院,副教授、博士生导师
代表性工作(一作或通讯*)
方向1:底层图像处理
[1] Xiangyu Rui, Xiangyong Cao*, Jun Shu, Qian Zhao, Deyu Meng*. A Hyper-weight Network for Hyperspectral Image Denoising. arXiv: 2301.06081 [pdf]
[2] Jin Cao, Xiangyong Cao*, Deyu Meng. Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers. arXiv: 2410.08688 [pdf][code]
[3] Jin Cao, Yi Cao, Li Pang, Deyu Meng, Xiangyong Cao*. HAIR: Hypernetworks-based All-in-One Image Restoration. arXiv: 2408.08091 [pdf][code]
[4] Man Zhou+, Keyu Yan+, Jinshan Pan, Wenqi Ren, Qi Xie, Xiangyong Cao*, Memory-augmented Deep Unfolding Network for Guided Image Super-resolution. International Journal of Computer Vision (IJCV), 2022. (+co-first author) [code] (CCF A)
[5] Xiangyong Cao, Yang Chen, Qian Zhao, Deyu Meng, Yao Wang, Dong Wang, Zongben Xu. Low-rank Matrix Factorization under General Mixture Noise Distributions. IEEE International Conference on Computer Vision (ICCV), 2015. [code] (Oral, CCF A)
[6] Zeyu Zhu, Xiangyong Cao*, Man Zhou, Junhao Huang, Deyu Meng. Probability-based Global Cross-modal Upsampling for Pan-sharpening. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [code] (CCF A)
[7] Xiangyong Cao, Qian Zhao, Deyu Meng, Yang Chen, Zongben Xu. Robust Low-rank Matrix Factorization under General Mixture Noise Distributions. IEEE Transactions on Image Processing (TIP), 25(10):4677-4690, 2016. [code] (CCF A)
[8] Xiangyong Cao+, Xueyang Fu+, Chen Xu, Deyu Meng. Deep Spatial-Spectral Global Reasoning Network for Hyperspectral Image Denoising. IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2021. (+co-first author) [code] (ESI高被引, CCF B,中科院1区)
[9] Xiangyong Cao, Xueyang Fu, Danfeng Hong, Zongben Xu, Deyu Meng. PanCSC-Net: A Model-Driven Deep Unfolding Method for Pansharpening. IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2021. (CCF B,中科院1区)
方向2:生成式遥感大模型及其应用
[1] Li Pang, , Xiangyong Cao*,Datao Tang, Xueru Bai, Feng Zhou, Shuang Xu, Deyu Meng. HSIGene: A Foundation Model For Hyperspectral Image Generation. arXiv:2409.12470. [pdf] [code]
[2] Datao Tang, Xiangyong Cao*, Xingsong Hou, Zhongyuan Jiang, Junmin Liu, Deyu Meng. CRS-Diff: Controllable Remote Sensing Image Generation with Diffusion Model. IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2024. [pdf] [code] (CCF B,中科院1区)
[3] Datao Tang, Xiangyong Cao*, Xuan Wu, Jialin Li, Jing Yao, Xueru Bai, Deyu Meng. AeroGen: Enhancing Remote Sensing Object Detection with Diffusion-Driven Data Generation. arXiv:2411.15497 [pdf][code]
[4] Xiangyu Rui, Xiangyong Cao*, Li Pang, Zongsheng Yue, Deyu Meng*. Unsupervised Hyperspectral Pansharpening via Low-rank Diffusion Models. Information Fusion, 2024. [pdf][code]
[5] Li Pang+, Xiangyu Rui+, Long Cui, Hongzhong Wang, Deyu Meng, Xiangyong Cao*. HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024. (+co-first author) [code] (CCF A)
[6] Gang Yang, Xiangyong Cao*, Wenzhe Xiao, Man Zhou, Aiping Liu*, Xun Chen, Deyu Meng. PanFlowNet: A Flow-Based Deep Network for Pan-sharpening. IEEE International Conference on Computer Vision (ICCV), 2023. [code] (CCF A)
[7] Jin Cao, Xiangyu Rui, Li Pang, Deyu Meng, Xiangyong Cao*. LatentHSI: Restore Hyperspectral Images in a Latent Space. Information Fusion, 2024.
方向3:遥感图像解译 (变化检测、语义分割、道路检测等)
[1] Kaiyu Li, Ruixun Liu, Xiangyong Cao*, Xueru Bai, Feng Zhou, Deyu Meng, Zhi Wang. SegEarth-OV: Towards Traning-Free Open-Vocabulary Segmentation for Remote Sensing Images. arXiv:2410.01768 [code]
[2] Kaiyu Li, Xiangyong Cao*, Yupeng Deng, Junmin Liu, Deyu Meng, Zhi Wang. SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector. IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2024. [pdf] [code]
[3] Kaiyu Li, Xiangyong Cao*, Deyu Meng. A New Learning Paradigm for Foundation Model-based Remote Sensing Change Detection. IEEE Transactions on Geoscience and Remote Sensing, 2024. [code] (ESI高被引, CCF B,中科院1区)
[4] Kaiyu Li+, Jiawei Jiang+, Andrea Codegoni+, Chengxi Han+, Yupeng Deng+, Keyan Chen+, Zhuo Zheng+, Hao Chen+, Zhengxia Zou, Zhenwei Shi, Sheng Fang, Deyu Meng, Zhi Wang, Xiangyong Cao. Open-CD: A Comprehensive Toolbox for Change Detection. arXiv:2407.15317. (+co-first author) [code]
[5] Xiangyong Cao, Feng Zhou, Lin Xu, Deyu Meng, Zongben Xu, John Paisley. Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network, IEEE Transactions on Image Processing (TIP), 27(5): 2354-2367, 2018. [code] (ESI高被引, CCF A)
[6] Xiangyong Cao, Jing Yao, Zongben Xu, Deyu Meng. Hyperspectral Image Classification with Convolutional Neural Network and Active Learning. IEEE Transactions on Geoscience and Remote Sensing (TGRS), 58(7): 4604-4616, 2020. [code] (ESI高被引, CCF B,中科院1区)
[7] Pan Yin+, Kaiyu Li+, Xiangyong Cao*, Jing Yao, Lei Liu, Xueru Bai, Feng Zhou, Deyu Meng. Towards Satellite Image Road Graph Extraction: A Global-Scale Dataset and A Novel Method. arXiv:2411.16733. [pdf] [code](+co-first author)
报告
[1] 高光谱图像处理中的稳健方法,Valse 2022 [slides] (提取码: z7m9)
[2] 基于噪声建模的高光谱图像去噪,Valse 2023 [slides] (提取码: zdw3)
[3] 生成式遥感大模型及其应用,Valse 2024 [slides] (提取码: tntd)
[4] 生成式遥感大模型及其应用,2024第三届中国数字地球大会 [slides] (提取码: tntd)
[5] 生成式遥感大模型及其应用,钱学森实验室研讨会 [slides] (提取码: tntd)
[6] 生成式遥感大模型及其应用,西电电子对抗教育部重点实验室研讨会 [slides] (提取码: tntd)
[7] Generative Remote Sensing Foundation Model and Its Applications,首届智慧遥感制图国际研讨会,香港大学 [slides] (提取码: 1111)