arXivDaily arXiv每日学术速递 周一至周五更新

大厂专区

2025-12-01 至 2025-12-01 共收录 1
2505.22195 2025-12-01 cs.CV

S2AFormer: Strip Self-Attention for Efficient Vision Transformer

S2AFormer:用于高效视觉变换器的条带自注意力

Guoan Xu, Wenfeng Huang, Wenjing Jia, Jiamao Li, Guangwei Gao, Guo-Jun Qi

机构 * Faculty of Engineering and Information Technology, University of Technology Sydney(工程与信息技术学院,悉尼大学) Bionic Vision System Laboratory, State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences(生物视觉系统实验室,传感技术国家重点实验室,上海微系统与信息技术研究所,中国科学院) PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology(PCA实验室,教育部高维信息智能感知与系统重点实验室,南京理工大学计算机科学与工程学院) Research Center for Industries of the Future and the School of Engineering, Westlake University(未来产业研究中心和工程学院,西湖大学) OPPO Research, Seattle, WA 98101 USA(OPPO研究,美国西雅图华盛顿州98101)

AI总结 S2AFormer通过引入条带自注意力机制,有效整合CNN的局部感知与Transformer的全局上下文建模,提升视觉变换器的效率与准确性。

Comments Accepted by IEEE-TIP, 14 pages, 8 figures, 9 tables

详情

展开后加载摘要…

URL PDF HTML 收藏