Cover Image

Multi-modal, multi-scale representation learning for satellite imagery analysis just needs a good ALiBi

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kage, Patrick, Andreadis, Pavlos
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

What DINO saw: ALiBi positional encoding reduces positional bias in Vision Transformers
by: Pawlowsky, Moritz, et al.
Published: (2026)

A Review of Pseudo-Labeling for Computer Vision
by: Kage, Patrick, et al.
Published: (2024)

Adaptive federated learning for ship detection across diverse satellite imagery sources
by: La, Tran-Vu, et al.
Published: (2025)

Towards multi-modal forgery representation learning for AI-generated video detection and localization
by: Le, Dat, et al.
Published: (2026)

A multi-modal dataset for insect biodiversity with imagery and DNA at the trap and individual level
by: Orsholm, Johanna, et al.
Published: (2025)

Post-hurricane building damage assessment using street-view imagery and structured data: A multi-modal deep learning approach
by: Xue, Zhuoqun, et al.
Published: (2024)

Cross-modal ultra-scale learning with tri-modalities of renal biopsy images for glomerular multi-disease auxiliary diagnosis
by: Long, Kaixing, et al.
Published: (2025)

Surgical Repair of Collapsed Attention Heads in ALiBi Transformers
by: Schallon, Palmer
Published: (2026)

Solar potential analysis over Indian cities using high-resolution satellite imagery and DEM
by: Singla, Jai
Published: (2024)

Anomaly detection in satellite imagery through temporal inpainting
by: Rouet-Leduc, Bertrand, et al.
Published: (2025)

Improving satellite imagery segmentation using multiple Sentinel-2 revisits
by: Jindgar, Kartik, et al.
Published: (2024)

Magnifying change: Rapid burn scar mapping with multi-resolution, multi-source satellite imagery
by: Sdraka, Maria, et al.
Published: (2026)

DeepDamageNet: A two-step deep-learning model for multi-disaster building damage segmentation and classification using satellite imagery
by: Alisjahbana, Irene, et al.
Published: (2024)

Addressing single object tracking in satellite imagery through prompt-engineered solutions
by: Psalta, Athena, et al.
Published: (2024)

Contrastive ground-level image and remote sensing pre-training improves representation learning for natural world imagery
by: Huynh, Andy V., et al.
Published: (2024)

Brightearth roads: Towards fully automatic road network extraction from satellite imagery
by: Duan, Liuyun, et al.
Published: (2024)

Envisioning global urban development with satellite imagery and generative AI
by: Sun, Kailai, et al.
Published: (2026)

What makes for good morphology representations for spatial omics?
by: Chelebian, Eduard, et al.
Published: (2024)

MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
by: Kinakh, Vitaliy, et al.
Published: (2023)

Anomaly detection for the identification of volcanic unrest in satellite imagery
by: Popescu, Robert Gabriel, et al.
Published: (2024)

IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale Benchmark
by: Cao, Zhe, et al.
Published: (2025)

MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery
by: Kneeland, Reese, et al.
Published: (2026)

KidSat: satellite imagery to map childhood poverty dataset and benchmark
by: Sharma, Makkunda, et al.
Published: (2024)

Can multimodal representation learning by alignment preserve modality-specific information?
by: Thoreau, Romain, et al.
Published: (2025)

Atomizer: Generalizing to new modalities by breaking satellite images down to a set of scalars
by: de Turckheim, Hugo Riffaud, et al.
Published: (2025)

Giving each task what it needs -- leveraging structured sparsity for tailored multi-task learning
by: Upadhyay, Richa, et al.
Published: (2024)

A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks
by: Udandarao, Vishaal, et al.
Published: (2025)

Model Stock: All we need is just a few fine-tuned models
by: Jang, Dong-Hwan, et al.
Published: (2024)

Predicting butterfly species presence from satellite imagery using soft contrastive regularisation
by: van der Plas, Thijs L, et al.
Published: (2025)

A baseline for machine-learning-based hepatocellular carcinoma diagnosis using multi-modal clinical data
by: Wang, Binwu, et al.
Published: (2025)

Object Affordance Recognition and Grounding via Multi-scale Cross-modal Representation Learning
by: Wan, Xinhang, et al.
Published: (2025)

Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset
by: You, Zhiyuan, et al.
Published: (2024)

A training regime to learn unified representations from complementary breast imaging modalities
by: Sharma, Umang, et al.
Published: (2024)

Towards Billion-scale Multi-modal Biometric Search
by: Koner, Arka, et al.
Published: (2026)

Multi-modal learning for geospatial vegetation forecasting
by: Benson, Vitus, et al.
Published: (2023)

GloSoFarID: Global multispectral dataset for Solar Farm IDentification in satellite imagery
by: Yang, Zhiyuan, et al.
Published: (2024)

Serial fusion of multi-modal biometric systems
by: Marcialis, Gian Luca, et al.
Published: (2024)

GAIA: A Global, Multi-modal, Multi-scale Vision-Language Dataset for Remote Sensing Image Analysis
by: Zavras, Angelos, et al.
Published: (2025)

Forest canopy height estimation from satellite RGB imagery using large-scale airborne LiDAR-derived training data and monocular depth estimation
by: Lai, Yongkang, et al.
Published: (2026)

Cross-modal learning for plankton recognition
by: Kareinen, Joona, et al.
Published: (2026)