Rethinking Transformers for Semantic Segmentation of Remote Sensing Images

计算机科学 编码器 增采样 人工智能 变压器 分割 卷积神经网络 模式识别(心理学) 计算机视觉 特征提取 图像(数学) 量子力学 操作系统 物理 电压
作者
Yuheng Liu,Yifan Zhang,Ye Wang,Shaohui Mei
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:61: 1-15 被引量:17
标识
DOI:10.1109/tgrs.2023.3302024
摘要

Transformer has been widely applied in image processing tasks as a substitute for Convolutional Neural Networks (CNNs) for feature extraction due to its superiority in global context modeling and flexibility in model generalization. However, the existing transformer-based methods for semantic segmentation of Remote Sensing (RS) images are still with several limitations, which can be summarized into two main aspects: 1) the transformer encoder is generally combined with CNN-based decoder, leading to inconsistency in feature representations; 2) the strategies for global and local context information utilization are not sufficiently effective. Therefore, in this paper, a Global-Local Transformer Segmentor (GLOTS) framework is proposed for semantic segmentation of RS images to acquire consistent feature representations by adopting transformers for both encoding and decoding, in which a Masked Image Modeling (MIM) pretrained transformer encoder is adopted to learn semantic-rich representations of input images, and a multi-scale global-local transformer decoder is designed to fully exploit the global and local features. Specifically, the transformer decoder uses a feature separation-aggregation module (FSAM) to utilize the feature adequately at different scales and adopts a global-local attention module (GLAM) containing Global Attention Block (GAB) and Local Attention Block (LAB) to capture the global and local context information respectively. Furthermore, a Learnable Progressive Upsampling Strategy (LPUS) is proposed to restore the resolution progressively, which can flexibly recover the fine-grained details in the upsampling process. Experimental results on the three benchmark RS datasets demonstrate that the proposed GLOTS is capable of achieving better performance with some state-of-the-art methods, and the superiority of the proposed framework is also verified by ablation studies. The code will be available at https://github.com/lyhnsn/GLOTS.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Sky完成签到,获得积分10
刚刚
静静子完成签到,获得积分10
刚刚
随安完成签到,获得积分20
刚刚
大意的雨双完成签到 ,获得积分10
刚刚
Dr.Shan完成签到,获得积分10
刚刚
JIASHOUSHOU完成签到,获得积分10
1秒前
一颗煤炭完成签到 ,获得积分10
1秒前
Cipher完成签到 ,获得积分10
2秒前
脑洞疼应助LIUYONG采纳,获得10
2秒前
可乐完成签到,获得积分10
2秒前
3秒前
koukousang完成签到,获得积分10
4秒前
乐乐应助张无缺采纳,获得10
5秒前
三三完成签到,获得积分10
5秒前
平常荷花完成签到 ,获得积分10
7秒前
量子星尘发布了新的文献求助10
8秒前
阿胡发布了新的文献求助30
8秒前
水晶李完成签到 ,获得积分10
9秒前
脑洞疼应助静静子采纳,获得100
12秒前
新年好完成签到,获得积分10
13秒前
爆米花应助Michelle采纳,获得10
16秒前
16秒前
LYSM应助晴栀采纳,获得10
17秒前
Bean完成签到,获得积分10
17秒前
17秒前
17秒前
幸福妙柏完成签到 ,获得积分10
18秒前
汕头凯奇完成签到,获得积分10
19秒前
aoba完成签到 ,获得积分10
20秒前
潇洒的平松完成签到,获得积分10
21秒前
qwer完成签到,获得积分10
21秒前
fduqyy发布了新的文献求助10
21秒前
csu_zs完成签到,获得积分10
21秒前
21秒前
LILYpig完成签到 ,获得积分10
22秒前
文静醉易完成签到,获得积分10
22秒前
无聊的翠芙完成签到,获得积分10
23秒前
zhangxuhns完成签到,获得积分10
24秒前
大力哈密瓜完成签到,获得积分10
24秒前
无花果应助碧蓝碧凡采纳,获得10
25秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038388
求助须知:如何正确求助?哪些是违规求助? 3576106
关于积分的说明 11374447
捐赠科研通 3305798
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029