Geospatial technologies are becoming increasingly essential in our world for a wide range of applications, including agriculture, urban planning, and disaster response. To help improve the applicability and performance of deep learning models on these geospatial tasks, various works have begun investigating foundation models for this domain. Researchers have explored two prominent approaches for introducing such models in geospatial applications, but both have drawbacks in terms of limited performance benefit or prohibitive training cost. Therefore, in this work, we propose a novel paradigm for building highly effective geospatial foundation models with minimal resource cost and carbon impact. We first construct a compact yet diverse dataset from multiple sources to promote feature diversity, which we term GeoPile. Then, we investigate the potential of continual pretraining from large-scale ImageNet-22k models and propose a multi-objective continual pretraining paradigm, which leverages the strong representations of ImageNet while simultaneously providing the freedom to learn valuable in-domain features. Our approach outperforms previous state-of-the-art geospatial pretraining methods in an extensive evaluation on seven downstream datasets covering various tasks such as change detection, classification, multi-label classification, semantic segmentation, and super-resolution.
CromSS: Cross-modal pre-training with noisy labels for remote sensing image segmentation
Technical University of Munich (TUM)（慕尼黑工业大学）；Remote Sensing Technology Institute, German Aerospace Center (DLR)（德国航空航天中心遥感技术研究所）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
CL-CLIP: CLIP-Based Continual Learning Framework with Cost-Volume Category Decoupling for Object Detection
National College for Excellent Engineers, Beihang University（卓越工程师学院，北京航空航天大学）；AI Research, Qihoo 360（360人工智能研究院，奇虎360）；School of Electronic Information Engineering, Beihang University（电子信息学院，北京航空航天大学）；School of Cyber Science and Technology, Beihang University（网络安全科学与技术学院，北京航空航天大学）；School of Computer Science and Engineering, Beihang University（计算机科学与工程学院，北京航空航天大学）；State Key Laboratory of Media Convergence and Communication, Communication University of China（媒体融合与传播国家重点实验室，中国传媒大学）；Institute of Information Technology, Mathematics and Mechanics, Lobachebsky University（信息技术、数学与力学学院，洛瓦茨基大学）；School of Artificial Intelligence, Beihang University（人工智能学院，北京航空航天大学）
GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI
IBM Research Europe（IBM欧洲研究院）；Technical University Munich（慕尼黑技术大学）；Clark University（克拉克大学）；MBZUAI；NASA Impact（NASA影响计划）；ESA Φ \Phi -lab（欧洲航天局Φ实验室）；Arizona State University（亚利桑那州立大学）；ServiceNow AI Research（ServiceNow人工智能研究）
McGill University（麦吉尔大学）；Facebook AI Research（脸书人工智能研究院）
This paper presents SPeCiaL: a method for unsupervised pretraining of representations tailored for continual learning. Our approach devises a meta-learning objective that differentiates through a sequential learning process. Specifically, we train a linear model over the representations to match different augmented views of the same image together, each view presented sequentially. The linear model is then evaluated on both its ability to classify images it just saw, and also on images from previous iterations. This gives rise to representations that favor quick knowledge retention with minima…
SIGMAE: A Spectral-Index-Guided Foundation Model for Multispectral Remote Sensing
School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；School of Artificial Intelligence and Automation, Wuhan University of Science and Technology（武汉科技大学人工智能与自动化学院）；School of Electronic Information, Wuhan University of Science and Technology（武汉科技大学电子信息学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）
GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Data
School of Earth and Space Sciences, Peking University（地球与空间科学学院，北京大学）；College of Urban and Environmental Sciences, Peking University（城市与环境科学学院，北京大学）；State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation, CAS（多模态人工智能系统国家重点实验室，中国科学院自动化研究所）；Intelligent Maintenance and Operations Systems Lab（智能维护与运营系统实验室）
ShanghaiTech University（上海科技大学）；Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（中国科学院上海微系统与信息技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；KU Leuven（鲁汶大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉成像工程技术研究中心）
Vision-language pre-training (VLP) has attracted increasing attention recently. With a large amount of image-text pairs, VLP models trained with contrastive loss have achieved impressive performance in various tasks, especially the zero-shot generalization on downstream datasets. In practical applications, however, massive data are usually collected in a streaming fashion, requiring VLP models to continuously integrate novel knowledge from incoming data and retain learned knowledge. In this work, we focus on learning a VLP model with sequential chunks of image-text pair data. To tackle the cat…
A Practitioner's Guide to Continual Multimodal Pretraining
Tübingen AI Center（蒂宾根人工智能中心）；University of Tübingen（蒂宾根大学）；Helmholtz Munich（亥姆霍兹慕尼黑中心）；University of Cambridge（剑桥大学）；LAION；Jülich Supercomputing Center (JSC)（于利希超级计算中心）；Research Center Jülich (FZJ)（于利希研究中心）；Helmholtz Association（亥姆霍兹联合会）；Google DeepMind（谷歌DeepMind）；Munich Center for ML（慕尼黑机器学习中心）；Technical University of Munich（慕尼黑工业大学）
Beyond Accuracy: Assessing Calibration of Geospatial Foundation Models and Their Sensitivity to Distribution Shifts
Technical University of Munich (TUM)（慕尼黑工业大学）；German Aerospace Center (DLR)（德国航空航天中心）；Massachusetts Institute of Technology (MIT)（麻省理工学院）；Taylor Geospatial（泰勒地理空间公司）
No One Knows the State of the Art in Geospatial Foundation Models
Taylor Geospatial（泰勒地理空间公司）；Technical University of Munich（慕尼黑技术大学）；Microsoft AI for Good Research Lab（微软AI for Good研究实验室）；Allen Institute for AI（艾伦人工智能研究所）；Vector Institute（向量研究所）；Carleton University（卡尔顿大学）；Clark University（克拉克大学）；University of British Columbia（不列颠哥伦比亚大学）；Arizona State University（亚利桑那州立大学）
Landslide Hazard Mapping with Geospatial Foundation Models: Geographical Generalizability, Data Scarcity, and Band Adaptability
School of Geographical Sciences and Urban Planning（地理科学与城市规划学院）；Arizona State University（亚利桑那州立大学）；School of Computing and Augmented Intelligence（计算与增强智能学院）；NASA Marshall Space Flight Center（国家航空航天局马歇尔航天飞行中心）
Microsoft Health Futures UK（微软健康未来英国）；Microsoft Health Futures US（微软健康未来美国）；Mayo Clinic M.D（梅奥诊所）；Radiology AI Lab, Mayo Clinic M.D（放射学AI实验室，梅奥诊所）；Microsoft Health & Life Sciences（微软健康与生命科学）；Cambridge University Hospitals M.D（剑桥大学医院）
Leveraging AI multimodal geospatial foundation models for improved near-real-time flood mapping at a global scale
North Carolina State University（北卡罗来纳州立大学）；LabCorp（实验室集团）；Humboldt-Universität zu Berlin（柏林洪堡大学）；Earth and Life Institute, UCLouvain（鲁汶天主教大学地球与生命研究所）；University of Helsinki（赫尔辛基大学）；Clark University（克拉克大学）；Thünen Institute of Farm Economics（蒂嫩农场经济研究所）
FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales
Biological and Environmental Science and Engineering Division, King Abdullah University of Science and Technology（国王阿卜杜勒·阿齐兹科技大学生物与环境科学与工程 division）；Computer, Electrical and Mathematical Science and Engineering Division, King Abdullah University of Science and Technology（国王阿卜杜勒·阿齐兹科技大学计算机、电气与数学科学与工程 division）
LLM Post-Training: A Deep Dive into Reasoning Large Language Models
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Central Florida（中佛罗里达大学）；University of California at Merced（加州大学默塞德分校）；Google DeepMind（谷歌DeepMind）；University of Oxford（牛津大学）
