Dual Sparse Aggregation Transformer for Multispectral Object Detection

作者
Wencong Wu,Xiuwei Zhang,Hanlin Yin,Hongxi Zhang,Yanning Zhang
出处
期刊:Cornell University - arXiv [Cornell University]
标识
DOI:10.48550/arxiv.2606.31015
摘要

Transformer-based approaches have obtained excellent performance in multispectral object detection tasks due to their ability to model long-range dependencies and capture complementary information. However, previous transformer-based multispectral detection methods tend to use all available tokens for similarity calculation, which results in redundant information interaction from irrelevant areas, leading to degraded detection performance. To overcome this challenge, we propose a novel Dual Sparse Aggregation Transformer (DSAFormer) for multispectral object detection, which consists of a Dual Sparse Transformer (DSFormer) and a Learnable Addition Fusion Block (LAFB). Specifically, the DSFormer is designed to exploit and boost cross-modal complementary information, thereby improving detection performance. It incorporates three key components: A Spatial Sparse Multi-Head Cross-Attention (SSMHCA) mechanism selectively captures cross-modal relationships at the spatial level by reserving only the high query-key similarity scores, eliminating irrelevant interactions. A Channel Sparse Multi-Head Cross-Attention (CSMHCA) mechanism performs similar sparse calculations at the channel level to enhance feature representation and filter out low matching query-key. A Multi-Scale Feature Refinement Layer (MSFRL) is developed to aggregate hierarchical features and suppress redundant information. To effectively fuse multimodal features, the LAFB is introduced to aggregate intramodal and intermodal feature information by feature reweighting. Extensive experimental results have demonstrated that our proposed DSAFormer achieves better detection performance against state-of-the-art methods on four public datasets, including the MFAD, FLIR, M$^3$FD, and LLVIP. The source code of our DSAFormer will be released at https://github.com/WenCongWu/DSAFormer.

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
难过的楼房完成签到,获得积分10
刚刚
熙熙1216完成签到,获得积分10
刚刚
1q完成签到,获得积分10
1秒前
小小发布了新的文献求助50
1秒前
希望天下0贩的0的应助被swimming采纳,获得100
1秒前
2秒前
2秒前
WATeam完成签到,获得积分10
3秒前
坚强孤容发布了新的文献求助10
3秒前
3秒前
4秒前
硝化菌_s完成签到,获得积分10
4秒前
爆米花的应助被yu采纳,获得10
4秒前
Akim的应助被知有采纳,获得10
4秒前
lizhengguang完成签到,获得积分10
5秒前
5秒前
chxhwu完成签到,获得积分10
5秒前
yjt发布了新的文献求助10
5秒前
biowzf完成签到,获得积分10
5秒前
Yang发布了新的文献求助10
6秒前
7秒前
8秒前
8秒前
8秒前
xuetian发布了新的文献求助10
8秒前
Shou完成签到,获得积分10
9秒前
CAOHOU的应助被魏伯璋采纳,获得10
9秒前
蛋黄蟹完成签到,获得积分20
10秒前
Jasper的应助被坦率紫烟采纳,获得10
10秒前
科研通AI6.4的应助被whisper采纳,获得10
11秒前
回旋加速喷气式阿姆斯特朗炮完成签到,获得积分20
11秒前
12秒前
文静冰海完成签到 ,获得积分10
12秒前
wand枘发布了新的文献求助10
12秒前
WATeam发布了新的文献求助10
14秒前
充电宝的应助被Yang采纳,获得10
14秒前
现代的bb发布了新的文献求助10
14秒前
14秒前
禾苗完成签到 ,获得积分10
14秒前
15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
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 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 8184240
求助须知:如何正确求助?哪些是违规求助? 9573297
关于积分的说明 21830585
捐赠科研通 7781300
什么是DOI,文献DOI怎么找? 3434285
关于科研通互助平台的介绍 2558389
邀请新用户注册赠送积分活动 2480814