XANet: An Efficient Remote Sensing Image Segmentation Model Using Element-Wise Attention Enhancement and Multi-Scale Attention Fusion
文献类型：期刊论文
| 作者 | Liang, Chenbin2,3,4 ; Xiao, Baihua3; Cheng, Bo1; Dong, Yunyun4
|
| 刊名 | REMOTE SENSING
 |
| 出版日期 | 2023 |
| 卷号 | 15期号:1页码:25 |
| 关键词 | semantic segmentation attention mechanism cross-attention feature fusion |
| DOI | 10.3390/rs15010236 |
| 通讯作者 | Dong, Yunyun(dongyunyun@snnu.edu.cn) |
| 英文摘要 | Massive and diverse remote sensing data provide opportunities for data-driven tasks in the real world, but also present challenges in terms of data processing and analysis, especially pixel-level image interpretation. However, the existing shallow-learning and deep-learning segmentation methods, bounded by their technical bottlenecks, cannot properly balance accuracy and efficiency, and are thus hardly scalable to the practice scenarios of remote sensing in a successful way. Instead of following the time-consuming deep stacks of local operations as most state-of-the-art segmentation networks, we propose a novel segmentation model with the encoder-decoder structure, dubbed XANet, which leverages the more computationally economical attention mechanism to boost performance. Two novel attention modules in XANet are proposed to strengthen the encoder and decoder, respectively, namely the Attention Recalibration Module (ARM) and Attention Fusion Module (AFM). Unlike current attention modules, which only focus on elevating the feature representation power, and regard the spatial and channel enhancement of a feature map as two independent steps, ARM gathers element-wise semantic descriptors coupling spatial and channel information to directly generate a 3D attention map for feature enhancement, and AFM innovatively utilizes the cross-attention mechanism for the sufficient spatial and channel fusion of multi-scale features. Extensive experiments were conducted on ISPRS and GID datasets to comprehensively analyze XANet and explore the effects of ARM and AFM. Furthermore, the results demonstrate that XANet surpasses other state-of-the-art segmentation methods in both model performance and efficiency, as ARM yields a superior improvement versus existing attention modules with a competitive computational overhead, and AFM achieves the complementary advantages of multi-level features under the sufficient consideration of efficiency. |
| 资助项目 | National Natural Science Foundation of China[62071469] ; National Natural Science Foundation of China[61731022] ; National Natural Science Foundation of China[71621002] ; National Natural Science Foundation of China[62001275] |
| WOS研究方向 | Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| 出版者 | MDPI |
| WOS记录号 | WOS:000909817900001 |
| 资助机构 | National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/51057]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_影像分析与机器视觉团队 |
| 通讯作者 | Dong, Yunyun |
| 作者单位 | 1.Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 4.Shaanxi Normal Univ, Northwest Land & Resource Res Ctr, Xian 710000, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liang, Chenbin,Xiao, Baihua,Cheng, Bo,et al. XANet: An Efficient Remote Sensing Image Segmentation Model Using Element-Wise Attention Enhancement and Multi-Scale Attention Fusion[J]. REMOTE SENSING,2023,15(1):25. |
| APA | Liang, Chenbin,Xiao, Baihua,Cheng, Bo,&Dong, Yunyun.(2023).XANet: An Efficient Remote Sensing Image Segmentation Model Using Element-Wise Attention Enhancement and Multi-Scale Attention Fusion.REMOTE SENSING,15(1),25. |
| MLA | Liang, Chenbin,et al."XANet: An Efficient Remote Sensing Image Segmentation Model Using Element-Wise Attention Enhancement and Multi-Scale Attention Fusion".REMOTE SENSING 15.1(2023):25. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。