Regression-Guided Refocusing Learning with Feature Alignment for Remote Sensing Tiny Object Detection

计算机科学 目标检测 人工智能 特征(语言学) 遥感 特征提取 计算机视觉 模式识别(心理学) 对象(语法) 地质学 语言学 哲学
作者
Ling Ge,Guanqun Wang,Tong Zhang,Yin Zhuang,He Chen,Hao Dong,Liang Chen
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:: 1-1
标识
DOI:10.1109/tgrs.2024.3407122
摘要

Tiny object detection is a formidable challenge in remote sensing intelligent interpretation. Tiny objects are usually fuzzy, densely distributed and highly sensitive to positioning errors, which leads to the mainstream detector usually achieving suboptimal detection performance when facing tiny objects. To address the mismatch of mainstream detector architectures and model optimization strategies in the context of tiny object detection, this paper presents an efficient and interpretable algorithm for tiny object detection, termed the Cross-Attention based Feature Fusion Enhanced tiny object detection Network (CAF 2 ENet). First, the cross-attention mechanism is introduced to refine the upsampling results of deep features. This refinement improves the precision of multi-scale feature fusion. Second, a training strategy named regression-based refocusing learning is introduced. Deviating from the conventional optimization strategy, our method guides the optimizer to prioritize higher-quality detection boxes by adjusting sample weights. This adjustment significantly amplifies the detector's potential to achieve superior detection results. Finally, the object composite confidence score is employed for the interpretable filtering of detection boxes. Extensive experiments on Tiny Object Detection in Aerial Images (AI-TOD) and object Detection in Optical Remote sensing images (DIOR) datasets are carried out, and comparison indicate that the proposed CAF 2 ENet can perform the remarkable performance compared to other state-of-the-art (SOTA) tiny object detection detectors, as it can reach 63.7% Average Precision ( AP 50 ) on AI-TOD and 75.4% AP 50 on DIOR, achieve SOTA performance.
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
蜂蜜罐zi发布了新的文献求助20
2秒前
大模型应助chun采纳,获得10
2秒前
2秒前
田様应助czc采纳,获得10
3秒前
英俊绝义发布了新的文献求助10
3秒前
斯文败类应助三石呦423采纳,获得10
3秒前
赘婿应助鲤鱼采纳,获得10
4秒前
4秒前
4秒前
4秒前
量子星尘发布了新的文献求助10
5秒前
小二郎应助Vincent采纳,获得10
5秒前
秉烛夜游完成签到,获得积分10
5秒前
吃的饱饱呀完成签到 ,获得积分10
6秒前
6秒前
lisiying完成签到,获得积分20
8秒前
8秒前
tjusasa发布了新的文献求助10
8秒前
英俊绝义完成签到,获得积分10
8秒前
要减肥的乌龟完成签到,获得积分10
9秒前
啊啊发布了新的文献求助10
9秒前
Zer完成签到,获得积分10
10秒前
lisiying发布了新的文献求助10
11秒前
11秒前
MchemG举报乐正熠彤求助涉嫌违规
12秒前
12秒前
路十三发布了新的文献求助10
13秒前
朵拉A梦完成签到,获得积分10
13秒前
14秒前
浅渊发布了新的文献求助10
14秒前
充电宝应助要减肥的乌龟采纳,获得10
14秒前
科研牛马完成签到,获得积分20
15秒前
彭于晏应助勤恳的访风采纳,获得10
15秒前
小马甲应助包子的开心采纳,获得10
16秒前
16秒前
LYB吕发布了新的文献求助20
16秒前
17秒前
科研牛马发布了新的文献求助10
19秒前
19秒前
yimiyangguang完成签到 ,获得积分10
20秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
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 3975814
求助须知:如何正确求助?哪些是违规求助? 3520123
关于积分的说明 11201020
捐赠科研通 3256502
什么是DOI,文献DOI怎么找? 1798347
邀请新用户注册赠送积分活动 877523
科研通“疑难数据库(出版商)”最低求助积分说明 806417