Dynamic multi-scale mixture-of-experts with cross-scale feature enhancement for UAV small object detection

计算机科学 人工智能 计算机视觉 目标检测 特征(语言学) 对象(语法) 模式识别(心理学) 特征提取 噪音(视频) 视频跟踪 领域(数学)
作者
Xiangyu Li,Zhiqiang Hou,Lingling Xiong,Sugang Ma,Yang Liu,Jianxiang Xi,Ruitao Lu
出处
期刊:Expert Systems With Applications [Elsevier BV]
卷期号:334: 134461-134461
标识
DOI:10.1016/j.eswa.2026.134461
摘要

Detecting small objects in unmanned aerial vehicle (UAV) imagery remains a persistent challenge due to scale variations of small objects in UAV scenarios and their low pixel occupancy. Existing approaches suffer from two issues in feature extraction and fusion. First, backbone networks employ fixed receptive fields, precluding input-adaptive adjustment and thereby failing to capture adequate contextual information for small objects. Second, cross-scale feature fusion predominantly relies on layer-by-layer chain propagation, which induces progressive degradation of high-resolution shallow details during transmission. Moreover, existing adaptive weighting mechanisms are restricted to channel-wise interactions between adjacent layers, lacking cross-layer semantic guidance and deep-level noise suppression; consequently, small object features are easily overwhelmed by large objects or background clutter. To address these issues, we propose DCE-DETR, a dedicated framework for UAV small object detection. For feature extraction, the Dynamic Multi-scale Mixture-of-Experts (DMS-MoE) adaptively selects optimal receptive field combinations through a dynamic routing mechanism that perceives global context, substantially enhancing scale perception. For feature fusion, the Gather-Scatter Pyramid Network (GSPN) adopts a middle-layer-centric nonlinear interaction architecture to shorten the transmission path between shallow details and deep semantics. Moreover, it integrates the Multi-scale Semantic Gated Attention (MSGA) module to enable cross-layer semantic guidance and suppress irrelevant noise. Extensive experiments on four public benchmarks, VisDrone2019, UAVDT, HazyDet, and SIMD, demonstrate consistent improvements of 3.0%, 2.4%, 2.6%, and 2.6% in AP over the baseline, alongside a 15.8% reduction in parameters.Under matched computational budgets, DCE-DETR significantly outperforms current state-of-the-art(SOTA) methods. Code and models are available at https://github.com/LXYSOD/DCE-DETR .
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
Zn发布了新的文献求助10
1秒前
LCX发布了新的文献求助10
1秒前
3秒前
CipherSage的应助被zeraphym采纳,获得10
4秒前
田様的应助被晨曦采纳,获得10
4秒前
Orange的应助被复杂幻梦采纳,获得10
5秒前
lnx发布了新的文献求助10
5秒前
tlc_191026发布了新的文献求助30
5秒前
kui完成签到,获得积分20
5秒前
bkagyin的应助被笑点低问安采纳,获得10
6秒前
聪明代曼完成签到,获得积分10
7秒前
温暖的千山完成签到 ,获得积分10
8秒前
Orange的应助被勤劳的凝梦采纳,获得10
8秒前
杨某完成签到,获得积分20
9秒前
11秒前
11秒前
科目三的应助被坚定的采波采纳,获得10
12秒前
科研通AI6.4的应助被晴天采纳,获得10
12秒前
张弛华发布了新的文献求助10
13秒前
LEETHEO发布了新的文献求助10
13秒前
赘婿的应助被科研通管家采纳,获得20
14秒前
科目三的应助被科研通管家采纳,获得10
14秒前
科研通AI2S的应助被科研通管家采纳,获得20
14秒前
Maestro_S的应助被科研通管家采纳,获得10
14秒前
null的应助被科研通管家采纳,获得10
14秒前
科目三的应助被科研通管家采纳,获得10
14秒前
Savananh_Xie的应助被科研通管家采纳,获得10
14秒前
14秒前
Lucas的应助被科研通管家采纳,获得10
15秒前
嘻嘻哈哈的应助被科研通管家采纳,获得10
15秒前
15秒前
Cr的应助被科研通管家采纳,获得10
15秒前
Cr的应助被科研通管家采纳,获得10
15秒前
15秒前
FashionBoy的应助被科研通管家采纳,获得10
15秒前
江亦旋发布了新的文献求助20
15秒前
Cr的应助被科研通管家采纳,获得10
15秒前
香蕉觅云的应助被科研通管家采纳,获得10
16秒前
SciGPT的应助被科研通管家采纳,获得10
16秒前
大模型的应助被科研通管家采纳,获得10
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
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 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 8183423
求助须知:如何正确求助?哪些是违规求助? 9572834
关于积分的说明 21827410
捐赠科研通 7780522
什么是DOI,文献DOI怎么找? 3434016
关于科研通互助平台的介绍 2558189
邀请新用户注册赠送积分活动 2480357