Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gong, Ziyang, Wei, Zhixiang, Wang, Di, Hu, Xiaoxing, Ma, Xianzheng, Chen, Hongruixuan, Jia, Yuru, Deng, Yupeng, Ji, Zhenming, Zhu, Xiangwei, Yang, Xue, Yokoya, Naoto, Zhang, Jing, Du, Bo, Yan, Junchi, Zhang, Liangpei
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.22629
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911170064023552
author Gong, Ziyang
Wei, Zhixiang
Wang, Di
Hu, Xiaoxing
Ma, Xianzheng
Chen, Hongruixuan
Jia, Yuru
Deng, Yupeng
Ji, Zhenming
Zhu, Xiangwei
Yang, Xue
Yokoya, Naoto
Zhang, Jing
Du, Bo
Yan, Junchi
Zhang, Liangpei
author_facet Gong, Ziyang
Wei, Zhixiang
Wang, Di
Hu, Xiaoxing
Ma, Xianzheng
Chen, Hongruixuan
Jia, Yuru
Deng, Yupeng
Ji, Zhenming
Zhu, Xiangwei
Yang, Xue
Yokoya, Naoto
Zhang, Jing
Du, Bo
Yan, Junchi
Zhang, Liangpei
contents The field of Remote Sensing Domain Generalization (RSDG) has emerged as a critical and valuable research frontier, focusing on developing models that generalize effectively across diverse scenarios. Despite the substantial domain gaps in RS images that are characterized by variabilities such as location, wavelength, and sensor type, research in this area remains underexplored: (1) Current cross-domain methods primarily focus on Domain Adaptation (DA), which adapts models to predefined domains rather than to unseen ones; (2) Few studies targeting the RSDG issue, especially for semantic segmentation tasks, where existing models are developed for specific unknown domains, struggling with issues of underfitting on other unknown scenarios; (3) Existing RS foundation models tend to prioritize in-domain performance over cross-domain generalization. To this end, we introduce the first vision foundation model for RSDG semantic segmentation, CrossEarth. CrossEarth demonstrates strong cross-domain generalization through a specially designed data-level Earth-Style Injection pipeline and a model-level Multi-Task Training pipeline. In addition, for the semantic segmentation task, we have curated an RSDG benchmark comprising 32 cross-domain settings across various regions, spectral bands, platforms, and climates, providing a comprehensive framework for testing the generalizability of future RSDG models. Extensive experiments on this benchmark demonstrate the superiority of CrossEarth over existing state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22629
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation
Gong, Ziyang
Wei, Zhixiang
Wang, Di
Hu, Xiaoxing
Ma, Xianzheng
Chen, Hongruixuan
Jia, Yuru
Deng, Yupeng
Ji, Zhenming
Zhu, Xiangwei
Yang, Xue
Yokoya, Naoto
Zhang, Jing
Du, Bo
Yan, Junchi
Zhang, Liangpei
Computer Vision and Pattern Recognition
The field of Remote Sensing Domain Generalization (RSDG) has emerged as a critical and valuable research frontier, focusing on developing models that generalize effectively across diverse scenarios. Despite the substantial domain gaps in RS images that are characterized by variabilities such as location, wavelength, and sensor type, research in this area remains underexplored: (1) Current cross-domain methods primarily focus on Domain Adaptation (DA), which adapts models to predefined domains rather than to unseen ones; (2) Few studies targeting the RSDG issue, especially for semantic segmentation tasks, where existing models are developed for specific unknown domains, struggling with issues of underfitting on other unknown scenarios; (3) Existing RS foundation models tend to prioritize in-domain performance over cross-domain generalization. To this end, we introduce the first vision foundation model for RSDG semantic segmentation, CrossEarth. CrossEarth demonstrates strong cross-domain generalization through a specially designed data-level Earth-Style Injection pipeline and a model-level Multi-Task Training pipeline. In addition, for the semantic segmentation task, we have curated an RSDG benchmark comprising 32 cross-domain settings across various regions, spectral bands, platforms, and climates, providing a comprehensive framework for testing the generalizability of future RSDG models. Extensive experiments on this benchmark demonstrate the superiority of CrossEarth over existing state-of-the-art methods.
title CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.22629