RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks
Remote sensing lightweight foundation models have achieved notable success in online perception within remote sensing. However, their capabilities are restricted to performing online inference solely based on their own observations and models, thus lacking a comprehensive understanding of large-scal...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-06 |
---|---|
Hauptverfasser: | , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Wang, Zhechao Cheng, Peirui Tian, Pengju Wang, Yuchao Chen, Mingxin Duan, Shujing Wang, Zhirui Li, Xinming Sun, Xian |
description | Remote sensing lightweight foundation models have achieved notable success in online perception within remote sensing. However, their capabilities are restricted to performing online inference solely based on their own observations and models, thus lacking a comprehensive understanding of large-scale remote sensing scenarios. To overcome this limitation, we propose a Remote Sensing Distributed Foundation Model (RS-DFM) based on generalized information mapping and interaction. This model can realize online collaborative perception across multiple platforms and various downstream tasks by mapping observations into a unified space and implementing a task-agnostic information interaction strategy. Specifically, we leverage the ground-based geometric prior of remote sensing oblique observations to transform the feature mapping from absolute depth estimation to relative depth estimation, thereby enhancing the model's ability to extract generalized features across diverse heights and perspectives. Additionally, we present a dual-branch information compression module to decouple high-frequency and low-frequency feature information, achieving feature-level compression while preserving essential task-agnostic details. In support of our research, we create a multi-task simulation dataset named AirCo-MultiTasks for multi-UAV collaborative observation. We also conduct extensive experiments, including 3D object detection, instance segmentation, and trajectory prediction. The numerous results demonstrate that our RS-DFM achieves state-of-the-art performance across various downstream tasks. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3067012113</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3067012113</sourcerecordid><originalsourceid>FETCH-proquest_journals_30670121133</originalsourceid><addsrcrecordid>eNqNys0KgkAUQOEhCJLyHS60FuYnNdpFJm3caHsxvIamMzV3pl4_Fz1Aq7M434IFUikR7XdSrlhINHDOZZLKOFYBK8sqyvLiAEcocTIOoUJNvb5D1pOz_c07bCE3XreN642GwrQ4QmfsDN5oCSEzHz1TbCa4NvSgDVt2zUgY_rpm2_x8PV2ipzUvj-TqwXir51UrnqRcSCGU-k99ASr8Pnw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3067012113</pqid></control><display><type>article</type><title>RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks</title><source>Free E- Journals</source><creator>Wang, Zhechao ; Cheng, Peirui ; Tian, Pengju ; Wang, Yuchao ; Chen, Mingxin ; Duan, Shujing ; Wang, Zhirui ; Li, Xinming ; Sun, Xian</creator><creatorcontrib>Wang, Zhechao ; Cheng, Peirui ; Tian, Pengju ; Wang, Yuchao ; Chen, Mingxin ; Duan, Shujing ; Wang, Zhirui ; Li, Xinming ; Sun, Xian</creatorcontrib><description>Remote sensing lightweight foundation models have achieved notable success in online perception within remote sensing. However, their capabilities are restricted to performing online inference solely based on their own observations and models, thus lacking a comprehensive understanding of large-scale remote sensing scenarios. To overcome this limitation, we propose a Remote Sensing Distributed Foundation Model (RS-DFM) based on generalized information mapping and interaction. This model can realize online collaborative perception across multiple platforms and various downstream tasks by mapping observations into a unified space and implementing a task-agnostic information interaction strategy. Specifically, we leverage the ground-based geometric prior of remote sensing oblique observations to transform the feature mapping from absolute depth estimation to relative depth estimation, thereby enhancing the model's ability to extract generalized features across diverse heights and perspectives. Additionally, we present a dual-branch information compression module to decouple high-frequency and low-frequency feature information, achieving feature-level compression while preserving essential task-agnostic details. In support of our research, we create a multi-task simulation dataset named AirCo-MultiTasks for multi-UAV collaborative observation. We also conduct extensive experiments, including 3D object detection, instance segmentation, and trajectory prediction. The numerous results demonstrate that our RS-DFM achieves state-of-the-art performance across various downstream tasks.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Collaboration ; Instance segmentation ; Mapping ; Object recognition ; Perception ; Remote sensing ; Unmanned aerial vehicles</subject><ispartof>arXiv.org, 2024-06</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by-sa/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Wang, Zhechao</creatorcontrib><creatorcontrib>Cheng, Peirui</creatorcontrib><creatorcontrib>Tian, Pengju</creatorcontrib><creatorcontrib>Wang, Yuchao</creatorcontrib><creatorcontrib>Chen, Mingxin</creatorcontrib><creatorcontrib>Duan, Shujing</creatorcontrib><creatorcontrib>Wang, Zhirui</creatorcontrib><creatorcontrib>Li, Xinming</creatorcontrib><creatorcontrib>Sun, Xian</creatorcontrib><title>RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks</title><title>arXiv.org</title><description>Remote sensing lightweight foundation models have achieved notable success in online perception within remote sensing. However, their capabilities are restricted to performing online inference solely based on their own observations and models, thus lacking a comprehensive understanding of large-scale remote sensing scenarios. To overcome this limitation, we propose a Remote Sensing Distributed Foundation Model (RS-DFM) based on generalized information mapping and interaction. This model can realize online collaborative perception across multiple platforms and various downstream tasks by mapping observations into a unified space and implementing a task-agnostic information interaction strategy. Specifically, we leverage the ground-based geometric prior of remote sensing oblique observations to transform the feature mapping from absolute depth estimation to relative depth estimation, thereby enhancing the model's ability to extract generalized features across diverse heights and perspectives. Additionally, we present a dual-branch information compression module to decouple high-frequency and low-frequency feature information, achieving feature-level compression while preserving essential task-agnostic details. In support of our research, we create a multi-task simulation dataset named AirCo-MultiTasks for multi-UAV collaborative observation. We also conduct extensive experiments, including 3D object detection, instance segmentation, and trajectory prediction. The numerous results demonstrate that our RS-DFM achieves state-of-the-art performance across various downstream tasks.</description><subject>Collaboration</subject><subject>Instance segmentation</subject><subject>Mapping</subject><subject>Object recognition</subject><subject>Perception</subject><subject>Remote sensing</subject><subject>Unmanned aerial vehicles</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNys0KgkAUQOEhCJLyHS60FuYnNdpFJm3caHsxvIamMzV3pl4_Fz1Aq7M434IFUikR7XdSrlhINHDOZZLKOFYBK8sqyvLiAEcocTIOoUJNvb5D1pOz_c07bCE3XreN642GwrQ4QmfsDN5oCSEzHz1TbCa4NvSgDVt2zUgY_rpm2_x8PV2ipzUvj-TqwXir51UrnqRcSCGU-k99ASr8Pnw</recordid><startdate>20240611</startdate><enddate>20240611</enddate><creator>Wang, Zhechao</creator><creator>Cheng, Peirui</creator><creator>Tian, Pengju</creator><creator>Wang, Yuchao</creator><creator>Chen, Mingxin</creator><creator>Duan, Shujing</creator><creator>Wang, Zhirui</creator><creator>Li, Xinming</creator><creator>Sun, Xian</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240611</creationdate><title>RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks</title><author>Wang, Zhechao ; Cheng, Peirui ; Tian, Pengju ; Wang, Yuchao ; Chen, Mingxin ; Duan, Shujing ; Wang, Zhirui ; Li, Xinming ; Sun, Xian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30670121133</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Collaboration</topic><topic>Instance segmentation</topic><topic>Mapping</topic><topic>Object recognition</topic><topic>Perception</topic><topic>Remote sensing</topic><topic>Unmanned aerial vehicles</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Zhechao</creatorcontrib><creatorcontrib>Cheng, Peirui</creatorcontrib><creatorcontrib>Tian, Pengju</creatorcontrib><creatorcontrib>Wang, Yuchao</creatorcontrib><creatorcontrib>Chen, Mingxin</creatorcontrib><creatorcontrib>Duan, Shujing</creatorcontrib><creatorcontrib>Wang, Zhirui</creatorcontrib><creatorcontrib>Li, Xinming</creatorcontrib><creatorcontrib>Sun, Xian</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Zhechao</au><au>Cheng, Peirui</au><au>Tian, Pengju</au><au>Wang, Yuchao</au><au>Chen, Mingxin</au><au>Duan, Shujing</au><au>Wang, Zhirui</au><au>Li, Xinming</au><au>Sun, Xian</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks</atitle><jtitle>arXiv.org</jtitle><date>2024-06-11</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Remote sensing lightweight foundation models have achieved notable success in online perception within remote sensing. However, their capabilities are restricted to performing online inference solely based on their own observations and models, thus lacking a comprehensive understanding of large-scale remote sensing scenarios. To overcome this limitation, we propose a Remote Sensing Distributed Foundation Model (RS-DFM) based on generalized information mapping and interaction. This model can realize online collaborative perception across multiple platforms and various downstream tasks by mapping observations into a unified space and implementing a task-agnostic information interaction strategy. Specifically, we leverage the ground-based geometric prior of remote sensing oblique observations to transform the feature mapping from absolute depth estimation to relative depth estimation, thereby enhancing the model's ability to extract generalized features across diverse heights and perspectives. Additionally, we present a dual-branch information compression module to decouple high-frequency and low-frequency feature information, achieving feature-level compression while preserving essential task-agnostic details. In support of our research, we create a multi-task simulation dataset named AirCo-MultiTasks for multi-UAV collaborative observation. We also conduct extensive experiments, including 3D object detection, instance segmentation, and trajectory prediction. The numerous results demonstrate that our RS-DFM achieves state-of-the-art performance across various downstream tasks.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-06 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_3067012113 |
source | Free E- Journals |
subjects | Collaboration Instance segmentation Mapping Object recognition Perception Remote sensing Unmanned aerial vehicles |
title | RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T11%3A13%3A00IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=RS-DFM:%20A%20Remote%20Sensing%20Distributed%20Foundation%20Model%20for%20Diverse%20Downstream%20Tasks&rft.jtitle=arXiv.org&rft.au=Wang,%20Zhechao&rft.date=2024-06-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3067012113%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3067012113&rft_id=info:pmid/&rfr_iscdi=true |