Implicit CLIP Prior Decoupling for Few-Shot Remote Sensing Image Segmentation

计算机科学 先验概率 人工智能 分割 杠杆(统计) 公制(单位) 遥感应用 特征(语言学) 图像分割 排名(信息检索) 模式识别(心理学) 计算机视觉 特征提取 数据挖掘 解耦(概率) 一般化 事先信息 高光谱成像 机器学习 地形 渲染(计算机图形) 光学(聚焦) 图像融合 秩(图论) 遥感 差异(会计) 熵(时间箭头) 可视化 像素 自编码 余弦相似度 欧几里德距离
作者
Zhiyu Jiang,Ye Yuan,Dandan Ma,Qi Wang,Yuan Yuan
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:63: 1-13 被引量:7
标识
DOI:10.1109/tgrs.2025.3617662
摘要

Few-Shot Segmentation (FSS) in remote sensing aims to achieve segmentation of novel categories in query images using limited annotated support images. Despite extensive research, the significant intra-class differences of remote sensing targets continue to hinder progress in this field. Pre-trained vision-language models (VLMs) possess strong generalization capabilities, and their cross-modal information can effectively mitigate intra-class variance issues. However, VLMs rarely focus on dense prediction tasks, and the complexity of remote sensing imagery limits the effectiveness of existing attempts on FSS tasks. To address this issue, this article proposes an Implicit CLIP Prior Decoupling Network (ICPD-Net), which mines effective cross-modal priors from VLMs and leverages ranking information to improve visual metric strategies. Specifically, the Implicit Prior Decoupling Module (IPDM) utilizes ambiguous foreground-background vision-language similarities to construct class-agnostic prompts, while employing a prior learner to mine implicit vision-language priors that alleviate intra-class differences. To fully leverage cross-modal information, the Reliable Feature Fusion Module (RFFM) utilizes vision-language priors to obtain high-confidence query features for fusion with support features, and further mitigating intra-class differences through self-support paradigm. Finally, the Dual Visual Priors Module (DVPM) introduces a novel rank information prior for visual feature measurement. This approach constructs an effective metric learning method by combining the ranking relationships of Euclidean distances between support-query features with the Normalized Discounted Cumulative Gain (NDCG) algorithm, while comprehensively exploring visual metric relationships through traditional cosine similarity prior. Extensive experiments on iSAID-5iand DLRSD-5idemonstrate that our method achieves significant improvements. Particularly under the 1-shot setting, our approach shows exceptional effectiveness, outperforming state-of-the-art methods by up to 11.48% on the iSAID-5i dataset. The code of ICPD-Net is available at https://github.com/yeh15/ICPD-Net.
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
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
Samuel发布了新的文献求助10
刚刚
宋村村发布了新的文献求助10
刚刚
1秒前
null的应助被taipingyang采纳,获得10
1秒前
1秒前
宋博贤发布了新的文献求助10
3秒前
NexusExplorer的应助被kklove采纳,获得10
3秒前
QIQI发布了新的文献求助10
3秒前
3秒前
4秒前
5秒前
5秒前
山水完成签到 ,获得积分10
5秒前
曾经尔岚发布了新的文献求助10
6秒前
LLLLLLLLL完成签到,获得积分10
6秒前
skylar发布了新的文献求助10
6秒前
7秒前
8秒前
华仔的应助被蓝天采纳,获得10
8秒前
愉快舞蹈发布了新的文献求助10
8秒前
汉堡包的应助被蓝天采纳,获得10
8秒前
不将就1345发布了新的文献求助10
8秒前
10秒前
少7完成签到 ,获得积分10
10秒前
Maestro_S的应助被机灵幻天采纳,获得10
11秒前
SciGPT的应助被追寻的寻菱采纳,获得10
11秒前
zcyuqing发布了新的文献求助10
12秒前
曾经尔岚完成签到,获得积分10
12秒前
今后的应助被wang5945采纳,获得10
12秒前
隐形曼青的应助被che66采纳,获得10
12秒前
xzjj完成签到,获得积分10
13秒前
聿小弟完成签到,获得积分10
13秒前
13秒前
jiusi完成签到 ,获得积分10
13秒前
恶毒的婆婆完成签到,获得积分10
13秒前
15秒前
15秒前
宋村村完成签到,获得积分10
16秒前
16秒前
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
What Else Can I Tell You?: A Pragmatic Study of English Rhetorical Questions as Discursive and Argumentative Acts 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8163614
求助须知:如何正确求助?哪些是违规求助? 9557702
关于积分的说明 21741573
捐赠科研通 7754282
什么是DOI,文献DOI怎么找? 3428275
关于科研通互助平台的介绍 2552989
邀请新用户注册赠送积分活动 2472923