VisproVG: Confidence-Aware Visual Prompting for Remote Sensing Visual Grounding

遥感 计算机科学 计算机视觉 地球遥感 人工智能 遥感应用 可视化 地质学 反射率 地球观测 接地 合成孔径雷达 雷达成像
作者
Xiaowen Zhang,Licheng Jiao,Lingling Li,Long Sun,X M Liu,Fang Liu,Mengjia Wang,Wenping Ma,Yuan Wu
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:64: 4410414-4410414
标识
DOI:10.1109/tgrs.2026.3698863
摘要

Remote sensing visual grounding (RSVG) models commonly rely on backbones pretrained on natural image datasets. However, the inherent domain gap between natural images and remote sensing imagery significantly degrades model transferability, particularly when RSVG training samples are limited. Existing approaches primarily focus on enhancing localization accuracy through multi-scale visual–textual alignment and process each image–text pair independently, which limits their generalization capability under constrained supervision. In this work, we propose VisproVG, a novel framework that explicitly incorporates category-aware visual priors into the linguistic stream to mitigate domain shift and data scarcity. Specifically, VisproVG introduces a sample-level visual prompting mechanism that retrieves instance-level visual cues from a dynamically maintained, category-specific memory bank, which serve as stable and interpretable visual priors. To further improve semantic consistency across feature scales, we incorporate a lightweight cross-scale semantic refinement module that performs hierarchical top–down refinement. Beyond architectural design, we conduct a systematic analysis of the relationship between decoder confidence and localization accuracy. The analysis indicates that low-confidence predictions, while accounting for only a small fraction of test samples, exhibit substantially greater potential for improvement. Motivated by this observation, we introduce a confidence-guided adaptive test-time augmentation (TTA) strategy that selectively applies augmentation to uncertain samples, achieving a favorable balance between accuracy gains and computational efficiency. Extensive experiments on three RSVG benchmarks demonstrate the effectiveness of the proposed VisproVG. Notably, on the small-scale RSVG-HR dataset, VisproVG surpasses the second-best method by 5.05% meanIoU, highlighting its robustness under limited training data. Our code are available at https://github.com/XiaowZhang00/VisproVG.

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
lulu大王完成签到,获得积分10
刚刚
bqys的应助被岳老师采纳,获得10
1秒前
1秒前
顾矜的应助被受伤的无敌采纳,获得10
2秒前
2秒前
ubless607的应助被Run采纳,获得10
2秒前
尼斯湖中的小水怪完成签到 ,获得积分10
2秒前
江大橘完成签到,获得积分10
2秒前
CYY完成签到,获得积分10
2秒前
李慧敏完成签到,获得积分10
4秒前
Luxi完成签到,获得积分10
4秒前
三月完成签到,获得积分10
5秒前
5秒前
6秒前
jjj完成签到,获得积分10
7秒前
7秒前
山复尔尔发布了新的文献求助10
7秒前
reiner完成签到 ,获得积分10
7秒前
shippou完成签到 ,获得积分10
8秒前
8秒前
Jason完成签到,获得积分10
8秒前
9秒前
荼蘼发布了新的文献求助50
9秒前
nini发布了新的文献求助10
9秒前
tutu发布了新的文献求助10
10秒前
山复尔尔发布了新的文献求助10
13秒前
伊祁夜明完成签到,获得积分10
13秒前
在水一方的应助被COCO采纳,获得10
13秒前
天天快乐的应助被CYY采纳,获得10
14秒前
14秒前
15秒前
dawwf完成签到,获得积分10
16秒前
如意的听露完成签到,获得积分10
19秒前
甜美月光的应助被dawwf采纳,获得10
19秒前
20秒前
20秒前
化身孤岛的鲸完成签到 ,获得积分10
20秒前
觞_殇完成签到,获得积分10
21秒前
荼蘼发布了新的文献求助30
21秒前
22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
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
plantTFDB 508
Resource Recovery Handbook 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 8175157
求助须知:如何正确求助?哪些是违规求助? 9566975
关于积分的说明 21789458
捐赠科研通 7769647
什么是DOI,文献DOI怎么找? 3431836
关于科研通互助平台的介绍 2556078
邀请新用户注册赠送积分活动 2477241