SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection

情态动词 计算机科学 对象(语法) 遥感 人工智能 计算机视觉 地理 化学 高分子化学
作者
Y. Li,Xiangyang Li,Yunheng Li,Yicheng Zhang,Yimian Dai,Qibin Hou,Ming–Ming Cheng,Jianwen Yang
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:1
标识
DOI:10.48550/arxiv.2412.20665
摘要

With the rapid advancement of remote sensing technology, high-resolution multi-modal imagery is now more widely accessible. Conventional Object detection models are trained on a single dataset, often restricted to a specific imaging modality and annotation format. However, such an approach overlooks the valuable shared knowledge across multi-modalities and limits the model's applicability in more versatile scenarios. This paper introduces a new task called Multi-Modal Datasets and Multi-Task Object Detection (M2Det) for remote sensing, designed to accurately detect horizontal or oriented objects from any sensor modality. This task poses challenges due to 1) the trade-offs involved in managing multi-modal modelling and 2) the complexities of multi-task optimization. To address these, we establish a benchmark dataset and propose a unified model, SM3Det (Single Model for Multi-Modal datasets and Multi-Task object Detection). SM3Det leverages a grid-level sparse MoE backbone to enable joint knowledge learning while preserving distinct feature representations for different modalities. Furthermore, it integrates a consistency and synchronization optimization strategy using dynamic learning rate adjustment, allowing it to effectively handle varying levels of learning difficulty across modalities and tasks. Extensive experiments demonstrate SM3Det's effectiveness and generalizability, consistently outperforming specialized models on individual datasets. The code is available at https://github.com/zcablii/SM3Det.
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
1秒前
Pharm给Pharm的求助进行了留言
1秒前
AntonioJ完成签到,获得积分10
2秒前
怕孤独的白凡完成签到,获得积分10
2秒前
nekoneko完成签到,获得积分10
4秒前
等待黎明发布了新的文献求助10
5秒前
Li完成签到,获得积分10
6秒前
6秒前
小满完成签到,获得积分10
6秒前
华仔应助linggggg采纳,获得10
6秒前
7秒前
李健应助小羊采纳,获得10
7秒前
huoxu完成签到,获得积分10
7秒前
7秒前
8秒前
李健应助Killor采纳,获得10
8秒前
8秒前
圣晟胜完成签到,获得积分10
8秒前
田様应助Ysj采纳,获得10
9秒前
9秒前
树莓发布了新的文献求助20
9秒前
ZGQ应助单薄皮卡丘采纳,获得10
10秒前
李健的小迷弟应助诺幽时采纳,获得10
10秒前
科研通AI2S应助flyingeagle134采纳,获得10
10秒前
FashionBoy应助Prospect采纳,获得10
10秒前
研友_VZG7GZ应助GLL采纳,获得10
10秒前
务实的苠完成签到,获得积分10
11秒前
义气幼珊发布了新的文献求助10
12秒前
13秒前
13秒前
liyi发布了新的文献求助10
13秒前
绿色催化发布了新的文献求助10
14秒前
lll关注了科研通微信公众号
14秒前
linggggg完成签到,获得积分10
14秒前
林静文完成签到 ,获得积分10
15秒前
16秒前
16秒前
17秒前
燃云发布了新的文献求助10
17秒前
ssc完成签到,获得积分10
17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
Effects of Two Weeks of Red Light Therapy on Choroidal Thickness and Axial Length in Young Adults 700
Positive Art Therapy Theory and Practice 600
Management and the Arts 510
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
Key mechanistic insights into the intramolecular C-H bond amination and double bond aziridination in sulfamate esters catalyzed by dirhodium tetracarboxylate complexes 500
The Neuroscience of Language 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7671675
求助须知:如何正确求助?哪些是违规求助? 9238739
关于积分的说明 19897640
捐赠科研通 7241112
什么是DOI,文献DOI怎么找? 3285090
关于科研通互助平台的介绍 2443358
邀请新用户注册赠送积分活动 2287276