Bibliographic Details
| Title: |
用于土地覆盖分割的多路径多尺度注意力网络. |
| Alternate Title: |
A multi-path and multi-scale attention network for land cover segmentation. |
| Authors: |
李 燕1 002200@nuist.edu.cn, 樊新宇1, 陈 芹1 fanxinyu7590@163.com |
| Source: |
Computer Engineering & Science / Jisuanji Gongcheng yu Kexue. Jan2026, Vol. 48 Issue 1, p108-118. 11p. |
| Subjects: |
Land use mapping, Convolutional neural networks, Transformer models, Computer vision, Artificial neural networks, Feature extraction |
| Abstract (English): |
In recent years, Transformers have made remarkable progress in the field of image recognition, yet they still face challenges in pixel-level segmentation tasks, primarily due to their insufficiently explicit and effective handling of local deviations. To address this issue, this paper proposes a multipath and multi-scale attention network, named DMANet. By integrating the strengths of convolutional neural network (CNN) and Transformers during the encoding phase, this network is capable of simultaneously capturing fine-grained local information and extensive global context from images, effectively enhancing feature extraction capabilities. The proposed interactive dual-branch structure enhances feature integration, improving the model's performance in dense prediction tasks. During the decoding phase, cross-layer feature fusion is implemented to enhance DMANet's ability to recognize complex objects. DMANet has demonstrated its exceptional performance and broad applicability in complex land cover segmentation tasks through experiments on Potsdam, GID-15, and L8 SPARCS datasets. [ABSTRACT FROM AUTHOR] |
| Abstract (Chinese): |
近年来,Transformer及其变种在图像识别领域已取得显著进展,但其在像素级分割任务中 仍面临挑战,主要原因在于它们对局部偏差的处理不够显式和有效。对此,提出了一种名为DMANet的 多路径多尺度注意力网络。该网络在编码阶段结合了卷积神经网络和Transformer的优势,能够同时捕 获图像的精细局部信息和广泛的全局上下文信息,有效地提升特征提取能力。提出的交互式双分支结构 加强了对特征的整合能力,提高网络模型在密集预测任务中的性能。在解码阶段实施跨层特征融合,增强 DMANet对复杂目标的识别能力。通过在Potsdam,GID-15和L8 SPARCS数据集上进行测试,DMANet 展示了其在复杂土地覆盖分割任务中的优异性能及广泛适用性. [ABSTRACT FROM AUTHOR] |
|
Copyright of Computer Engineering & Science / Jisuanji Gongcheng yu Kexue is the property of Computer Engineering & Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Engineering Source |
