Clustering Guided Domain-Specific Pretrained Foundation Model for Very High-Resolution Arctic Remote Sensing

• URL: http://arxiv.org/abs/2605.30467v2
• Date: Wed, 03 Jun 2026 22:12:16 GMT
• Title: Clustering Guided Domain-Specific Pretrained Foundation Model for Very High-Resolution Arctic Remote Sensing
• Abstract summary: This study introduces a novel Arctic-focused remote sensing foundation model (RSFM)<n>It combines diversity-aware regional-scale image curation with masked autoencoder (MAE) self-supervised pretraining of a Vision Transformer ( VHSR) encoder for satellite image analysis.<n>We pretrained a ViT-Large encoder on the curated corpus using a domain-adapted MAE reconstruction objective, producing Arctic-specific transformer weights for downstream feature mapping.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This study introduces a novel Arctic-focused remote sensing foundation model (RSFM) by combining diversity-aware regional-scale image curation with masked autoencoder (MAE) self-supervised pretraining of a Vision Transformer (ViT) encoder for very-high-spatial-resolution (VHSR) satellite image analysis. Spectral and acquisition-metadata descriptors were used in a scalable affinity-propagation clustering workflow to select approximately 3 million chips from 267 TB of Vantor VHSR imagery This curation strategy was designed to reduce oversampling of visually repetitive or low-information areas while preserving broad scene diversity across the study domain. We pretrained a ViT-Large encoder on the curated corpus using a domain-adapted MAE reconstruction objective, producing Arctic-specific transformer weights for downstream feature mapping. The pretrained encoder was integrated into an existing location-aware detection and segmentation framework and evaluated across four hand-labeled Arctic datasets. Compared to ImageNet-initialized ViT-Large baseline, Arctic MAE pretraining produced consistent improvements in foreground mean F1 scores of 0.87, 0.72, 0.93, and 0.87, for infrastructure, IWP, RTS, and TCNs, with approximately 5-8 percentage increase. The proposed model also outperformed Prithvi-EO-2.0 in all downstream comparisons, with the smallest gain corresponding to at least a 15 percentage improvement mean F1, suggesting that domain-specific self-supervised pretraining on curated Arctic VHSR imagery provides more transferable representations for fine-scale Arctic mapping than a general-purpose Earth observation foundation model. These results demonstrate that optimizing the pretraining data distribution at regional scale, while keeping the architecture and MAE objective fixed, can produce a reusable Arctic-domain encoder for multiple VHSR remote sensing applications.

Related papers

• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales [65.4821703903285]
  FLORO is a multimodal foundation model designed to learn transferable representations from a small but highly diverse remote sensing corpus.<n> FLORO is pretrained using masked autoencoding on a heterogeneous combination of Sentinel-1, Sentinel-2, SkySAT imagery, elevation, and UAV-derived data.<n>We evaluated FLORO on the PANGAEA benchmark under a frozen-encoder protocol across scene classification, segmentation, and regression tasks.
  arXiv  Detail & Related papers  (2026-05-27T08:55:54Z)
• Improved Baselines with Representation Autoencoders [61.47127824064028]
  Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders.<n>We find three insights which simplify and improve RAE.<n> RAEv2 leads to more than 10x faster convergence over the original RAE.
  arXiv  Detail & Related papers  (2026-05-18T12:42:34Z)
• Efficient Hybrid CNN-GNN Architecture for Monocular Depth Estimation [0.0]
  We present GraphDepth, a monocular depth estimation architecture that integrates Graph Neural Networks (GNNs) within a convolutional encoder-decoder framework.<n>Our approach embeds efficient GraphSAGE layers at multiple scales of a ResNet-101 U-Net backbone.<n> Experiments on NYU Depth V2, WHU Aerial, ETH3D, and Mid-Air benchmarks demonstrate competitive accuracy within 4.6% of state-of-the-art transformers.
  arXiv  Detail & Related papers  (2026-05-11T09:21:04Z)
• VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors [49.39553550491549]
  We present VFMRecon, the first attempt to bridge transferable VFM priors with scaleconsistent requirements in scene-level neural reconstruction.<n> Specifically, we first introduce a lightweight scale alignment stage that restores multiview scale coherence.<n>We then integrate pretrained VFM features into the neural volumetric reconstruction pipeline via lightweight task-specific adapters.
  arXiv  Detail & Related papers  (2026-03-13T05:00:44Z)
• SFP: Real-World Scene Recovery Using Spatial and Frequency Priors [84.27251794411673]
  Scene recovery serves as a critical task for various computer vision applications.<n>We propose Spatial and Frequency Priors (SFP) for real-world scene recovery.
  arXiv  Detail & Related papers  (2025-12-09T05:24:25Z)
• Post-Disaster Affected Area Segmentation with a Vision Transformer (ViT)-based EVAP Model using Sentinel-2 and Formosat-5 Imagery [0.0]
  We propose a vision transformer (ViT)-based deep learning framework to refine disaster-affected area segmentation from remote sensing imagery.<n>Our framework improves the smoothness and reliability of segmentation results, offering a scalable approach for disaster mapping when accurate ground truth is unavailable.
  arXiv  Detail & Related papers  (2025-07-21T07:48:07Z)
• Pan-Arctic Permafrost Landform and Human-built Infrastructure Feature Detection with Vision Transformers and Location Embeddings [1.2895931807247418]
  Vision Transformers (ViTs) offer advantages in capturing long-range dependencies and global context via attention mechanisms.<n>ViTs support pretraining via self-supervised learning-addressing the common limitation of labeled data in Arctic feature detection.<n>This work investigates: (1) the suitability of pre-trained ViTs as feature extractors for high-resolution Arctic remote sensing tasks, and (2) the benefit of combining image and location embeddings.
  arXiv  Detail & Related papers  (2025-06-03T13:34:01Z)
• NeRF-VIO: Map-Based Visual-Inertial Odometry with Initialization Leveraging Neural Radiance Fields [14.294558959621892]
  A prior map serves as a foundational reference for localization in context-aware applications such as augmented reality (AR)<n>We propose a map-based visual-inertial localization algorithm (NeRF-VIO)<n>By integrating a two-stage update mechanism within a multi-state constraint Kalman filter (MSCKF) framework, the state of NeRF-VIO is constrained by both captured images from an onboard camera and rendered images from a pre-trained NeRF model.
  arXiv  Detail & Related papers  (2025-03-11T01:23:22Z)
• RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model [59.37279559684668]
  We introduce RS-vHeat, an efficient multi-modal remote sensing foundation model.<n>Specifically, RS-vHeat applies the Heat Conduction Operator (HCO) with a complexity of $O(N1.5)$ and a global receptive field.<n>Compared to attention-based remote sensing foundation models, we reduce memory usage by 84%, FLOPs by 24% and improves throughput by 2.7 times.
  arXiv  Detail & Related papers  (2024-11-27T01:43:38Z)
• Sub-token ViT Embedding via Stochastic Resonance Transformers [51.12001699637727]
  Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. We propose a training-free method inspired by "stochastic resonance" The resulting "Stochastic Resonance Transformer" (SRT) retains the rich semantic information of the original representation, but grounds it on a finer-scale spatial domain, partly mitigating the coarse effect of spatial tokenization.
  arXiv  Detail & Related papers  (2023-10-06T01:53:27Z)

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.