A Multiscale Grouping Transformer With CLIP Latents for Remote Sensing Image Captioning

隐藏字幕 计算机科学 遥感 变压器 计算机视觉 人工智能 图像(数学) 计算机图形学(图像) 地质学 工程类 电气工程 电压
作者
Lingwu Meng,Jing Wang,Ran Meng,Yang Yang,Liang Xiao
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:62: 1-15 被引量:2
标识
DOI:10.1109/tgrs.2024.3385500
摘要

Recent progress has shown that integrating multiscale visual features with advanced Transformer architectures is a promising approach for remote sensing image captioning (RSIC). However, the lack of local modeling ability in self-attention may potentially lead to inaccurate contextual information. Moreover, the scarcity of trainable image-caption pairs poses challenges in effectively harnessing the semantic alignment between images and texts. To mitigate these issues, we propose a Multiscale Grouping Transformer with Contrastive Language-Image Pre-training (CLIP) latents (MG-Transformer) for RSIC. First of all, a CLIP image embedding and a set of region features are extracted within a Multi-level Feature Extraction module. To achieve a comprehensive image representation, a Semantic Correlation module is designed to integrate the image embedding and region features with an attention gate. Subsequently, the integrated image features are fed into a Transformer model. The Transformer encoder utilizes dilated convolutions with different dilation rates to obtain multiscale visual features. To enhance the local modeling ability of the self-attention mechanism in the encoder, we introduce a Global Grouping Attention mechanism. This mechanism incorporates a grouping operation into self-attention, allowing each attention head to focus on different contextual information. The Transformer decoder then adopts the Meshed Cross-Attention mechanism to establish relationships between various scales of visual features and text features. This facilitates the generation of captions for images by the decoder. Experimental results on three RSIC datasets demonstrate the superiority of the proposed MG-Transformer. The code will be publicly available at https://github.com/One-paper-luck/MG-Transformer.
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
刚刚
彬琪发布了新的文献求助10
1秒前
1秒前
2秒前
2秒前
雨木目完成签到,获得积分10
3秒前
小鱼完成签到,获得积分10
3秒前
chenkaixin发布了新的文献求助10
3秒前
梦XING完成签到 ,获得积分10
4秒前
eternity136发布了新的文献求助10
4秒前
vv完成签到,获得积分10
5秒前
5秒前
哈哈哈哈发布了新的文献求助20
5秒前
KANG完成签到,获得积分10
6秒前
义气黄焖排骨完成签到,获得积分10
6秒前
7秒前
如梦如画发布了新的文献求助10
7秒前
Hannes应助15902933324sjc采纳,获得10
8秒前
8秒前
8秒前
梓默完成签到 ,获得积分10
8秒前
我是老大应助Japan采纳,获得10
9秒前
彬琪完成签到,获得积分10
9秒前
红尘踏歌完成签到,获得积分10
9秒前
不忘初心发布了新的文献求助10
10秒前
18746005898完成签到 ,获得积分10
10秒前
chenkaixin完成签到,获得积分10
11秒前
WangZhen完成签到,获得积分20
12秒前
乔木木完成签到,获得积分10
12秒前
一路畅通accept完成签到,获得积分10
12秒前
潇湘学术完成签到,获得积分10
12秒前
烂漫的如冬完成签到,获得积分10
13秒前
koi发布了新的文献求助10
13秒前
15秒前
15秒前
罗小马完成签到 ,获得积分10
15秒前
16秒前
wyg117完成签到,获得积分10
17秒前
CipherSage应助Zard采纳,获得10
17秒前
18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 4038619
求助须知:如何正确求助?哪些是违规求助? 3576294
关于积分的说明 11375058
捐赠科研通 3306084
什么是DOI,文献DOI怎么找? 1819374
邀请新用户注册赠送积分活动 892698
科研通“疑难数据库(出版商)”最低求助积分说明 815066