Knowledge Commons of Institute of Automation,CAS
Dual Attention Feature Fusion for Visible-Infrared Object Detection | |
Hu Yuxuan1,2![]() ![]() ![]() | |
2023-09 | |
会议名称 | 2023 International Conference on Artificial Neural Networks |
会议日期 | 2023-9 |
会议地点 | Heraklion, Greece |
摘要 | Feature fusion is an essential component of multimodal object detection to exploit the complementary information and common information between multi-source images. When it comes to visible-infrared image pairs, however, the visible images are prone to illumination and visibility and there may be a lot of interference information and little useful information. We suggest performing common feature enhancement and spatial cross attention sequentially to solve this problem. For this purpose, a novel Dual Attention Transformer Feature Fusion (DATFF) module which is designed for feature fusion of intermediate feature maps is proposed. We integrate it into two-stream object detectors and achieve state-of-the-art performance on DroneVehicle and FLIR visible-infrared object detection datasets. Our code is available at https://github.com/a21401624/DATFF. |
关键词 | Feature fusion Visible-infrared Object detection |
收录类别 | EI |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | 多模态协同认知 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56568 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Weng Lubin |
作者单位 | 1.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 3.Research Center of Aerospace Information, Institute of Automation, Chinese Academy of Sciences, Beijing, China 4.Institute of Information Fusion, Naval Aviation University, Yantai, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Hu Yuxuan,Shi Limin,Yao Libo,et al. Dual Attention Feature Fusion for Visible-Infrared Object Detection[C],2023. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Dual_Attention_Featu(3058KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论