SatelliteCalculator: A Multi-Task Vision Foundation Model for Quantitative Remote Sensing Inversion

• URL: http://arxiv.org/abs/2504.13442v1
• Date: Fri, 18 Apr 2025 03:48:04 GMT
• Title: SatelliteCalculator: A Multi-Task Vision Foundation Model for Quantitative Remote Sensing Inversion
• Authors: Zhenyu Yu, Mohd. Yamani Idna Idris, Pei Wang,
• Abstract summary: We introduce SatelliteCalculator, the first vision foundation model for quantitative remote sensing inversion.<n>By leveraging physically defined index adapters, we automatically construct a large-scale dataset of over one million paired samples.<n> Experiments demonstrate that SatelliteCalculator achieves competitive accuracy across all tasks while significantly reducing inference cost.
• Score: 4.824120664293887
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantitative remote sensing inversion plays a critical role in environmental monitoring, enabling the estimation of key ecological variables such as vegetation indices, canopy structure, and carbon stock. Although vision foundation models have achieved remarkable progress in classification and segmentation tasks, their application to physically interpretable regression remains largely unexplored. Furthermore, the multi-spectral nature and geospatial heterogeneity of remote sensing data pose significant challenges for generalization and transferability. To address these issues, we introduce SatelliteCalculator, the first vision foundation model tailored for quantitative remote sensing inversion. By leveraging physically defined index formulas, we automatically construct a large-scale dataset of over one million paired samples across eight core ecological indicators. The model integrates a frozen Swin Transformer backbone with a prompt-guided architecture, featuring cross-attentive adapters and lightweight task-specific MLP decoders. Experiments on the Open-Canopy benchmark demonstrate that SatelliteCalculator achieves competitive accuracy across all tasks while significantly reducing inference cost. Our results validate the feasibility of applying foundation models to quantitative inversion, and provide a scalable framework for task-adaptive remote sensing estimation.

Related papers

• A Survey on Remote Sensing Foundation Models: From Vision to Multimodality [35.532200523631765]
  Vision and multimodal foundation models for remote sensing have significantly improved the capabilities of intelligent geospatial data interpretation.<n>The diversity in data types, the need for large-scale annotated datasets, and the complexity of multimodal fusion techniques pose significant obstacles to the effective deployment of these models.<n>This paper provides a review of the state-of-the-art in vision and multimodal foundation models for remote sensing, focusing on their architecture, training methods, datasets and application scenarios.
  arXiv  Detail & Related papers  (2025-03-28T01:57:35Z)
• RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing [28.488986896516284]
  RoMA is a framework that enables scalable self-supervised pretraining of RS foundation models using large-scale, diverse, unlabeled data. RoMA enhances scalability for high-resolution images through a tailored auto-regressive learning strategy. experiments across scene classification, object detection, and semantic segmentation tasks demonstrate that RoMA-pretrained Mamba models consistently outperform ViT-based counterparts in both accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2025-03-13T14:09:18Z)
• UrbanSAM: Learning Invariance-Inspired Adapters for Segment Anything Models in Urban Construction [51.54946346023673]
  Urban morphology is inherently complex, with irregular objects of diverse shapes and varying scales.<n>The Segment Anything Model (SAM) has shown significant potential in segmenting complex scenes.<n>We propose UrbanSAM, a customized version of SAM specifically designed to analyze complex urban environments.
  arXiv  Detail & Related papers  (2025-02-21T04:25:19Z)
• WasteGAN: Data Augmentation for Robotic Waste Sorting through Generative Adversarial Networks [7.775894876221921]
  We introduce a data augmentation method based on a novel GAN architecture called wasteGAN. The proposed method allows to increase the performance of semantic segmentation models, starting from a very limited bunch of labeled examples. We then leverage the higher-quality segmentation masks predicted from models trained on the wasteGAN synthetic data to compute semantic-aware grasp poses.
  arXiv  Detail & Related papers  (2024-09-25T15:04:21Z)
• GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models [56.63218531256961]
  We introduce GenBench, a benchmarking suite specifically tailored for evaluating the efficacy of Genomic Foundation Models. GenBench offers a modular and expandable framework that encapsulates a variety of state-of-the-art methodologies. We provide a nuanced analysis of the interplay between model architecture and dataset characteristics on task-specific performance.
  arXiv  Detail & Related papers  (2024-06-01T08:01:05Z)
• Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection [55.2480439325792]
  We present an in-depth evaluation of an object detection model that integrates the LSKNet backbone with the DiffusionDet head. The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement. This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis.
  arXiv  Detail & Related papers  (2023-11-21T19:49:13Z)
• GEO-Bench: Toward Foundation Models for Earth Monitoring [139.77907168809085]
  We propose a benchmark comprised of six classification and six segmentation tasks. This benchmark will be a driver of progress across a variety of Earth monitoring tasks.
  arXiv  Detail & Related papers  (2023-06-06T16:16:05Z)
• MetaGraspNet: A Large-Scale Benchmark Dataset for Vision-driven Robotic Grasping via Physics-based Metaverse Synthesis [78.26022688167133]
  We present a large-scale benchmark dataset for vision-driven robotic grasping via physics-based metaverse synthesis. The proposed dataset contains 100,000 images and 25 different object types. We also propose a new layout-weighted performance metric alongside the dataset for evaluating object detection and segmentation performance.
  arXiv  Detail & Related papers  (2021-12-29T17:23:24Z)
• Benchmarking Unsupervised Object Representations for Video Sequences [111.81492107649889]
  We compare the perceptual abilities of four object-centric approaches: ViMON, OP3, TBA and SCALOR. Our results suggest that the architectures with unconstrained latent representations learn more powerful representations in terms of object detection, segmentation and tracking. Our benchmark may provide fruitful guidance towards learning more robust object-centric video representations.
  arXiv  Detail & Related papers  (2020-06-12T09:37:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.