Axial Cross Attention Meets CNN: Bibranch Fusion Network for Change Detection

计算机科学 人工智能 增采样 卷积神经网络 特征提取 保险丝(电气) 模式识别(心理学) 计算机视觉 像素 图像(数学) 电气工程 工程类
作者
Lei Song,Min Xia,Liguo Weng,Haifeng Lin,Ming Qian,Binyu Chen
出处
期刊:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:16: 21-32 被引量:53
标识
DOI:10.1109/jstars.2022.3224081
摘要

In the previous years, vision transformer has demonstrated a global information extraction capability in the field of computer vision that convolutional neural network (CNN) lacks. Due to the lack of inductive bias in vision transformer, it requires a large amount of data to support its training. In the field of remote sensing, it costs a lot to obtain a significant number of high-resolution remote sensing images. Most existing change detection networks based on deep learning rely heavily on the CNN, which cannot effectively utilize the long-distance dependence between pixels for difference discrimination. Therefore, this work aims to use a high-performance vision transformer to conduct change detection research with limited data. A bibranch fusion network based on axial cross attention (ACABFNet) is proposed. The network extracts local and global information of images through the CNN branch and transformer branch, respectively, and then, fuses local and global features by the bidirectional fusion approach. In the upsampling stage, similar feature information and difference feature information of the two branches are explicitly generated by feature addition and feature subtraction. Considering that the self-attention mechanism is not efficient enough for global attention over small datasets, we propose the axial cross attention. First, global attention along the height and width dimensions of images is performed respectively, and then cross attention is used to fuse the global feature information along two dimensions. Compared with the original self-attention, the structure is more graphics processing unit friendly and efficient. Experimental results on three datasets reveal that the ACABFNet outperforms existing change detection algorithms.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
Judy发布了新的文献求助20
刚刚
缥缈傲南完成签到,获得积分10
1秒前
Jasper应助无情的宛儿采纳,获得10
1秒前
萤照夜清完成签到,获得积分20
2秒前
2秒前
4秒前
薰硝壤应助默欢采纳,获得20
4秒前
4秒前
4秒前
4秒前
4秒前
jin完成签到 ,获得积分10
5秒前
小鱼yyy发布了新的文献求助20
7秒前
哈哈哈发布了新的文献求助10
9秒前
陈功完成签到,获得积分10
10秒前
搞怪路人完成签到 ,获得积分10
10秒前
CipherSage应助Judy采纳,获得10
10秒前
人间理想发布了新的文献求助10
11秒前
SciGPT应助小刺猬采纳,获得10
11秒前
12秒前
13秒前
科研通AI2S应助潮人采纳,获得10
14秒前
wp完成签到 ,获得积分10
14秒前
崔大胖发布了新的文献求助10
17秒前
19秒前
黎明完成签到,获得积分20
21秒前
22秒前
23秒前
23秒前
24秒前
研友_qZ6wg8发布了新的文献求助10
25秒前
26秒前
Jasper应助科研通管家采纳,获得10
26秒前
Lucas应助科研通管家采纳,获得10
26秒前
JamesPei应助科研通管家采纳,获得10
26秒前
深情安青应助科研通管家采纳,获得10
26秒前
今后应助科研通管家采纳,获得10
26秒前
思源应助科研通管家采纳,获得10
26秒前
小马甲应助科研通管家采纳,获得10
26秒前
桐桐应助科研通管家采纳,获得10
26秒前
高分求助中
Sustainability in Tides Chemistry 2000
Microlepidoptera Palaearctica, Volumes 1 and 3 - 13 (12-Volume Set) [German] 1122
Дружба 友好报 (1957-1958) 1000
The Data Economy: Tools and Applications 1000
A Dissection Guide & Atlas to the Rabbit 600
中国心血管健康与疾病报告2023(要完整的报告) 500
Development of a new synthetic process for the synthesis of (S)-methadone and (S)- and (R)-isomethadone as NMDA receptor antagonists for the treatment of depression 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3102764
求助须知:如何正确求助?哪些是违规求助? 2754003
关于积分的说明 7626148
捐赠科研通 2406815
什么是DOI,文献DOI怎么找? 1277007
科研通“疑难数据库(出版商)”最低求助积分说明 617041
版权声明 599103