Image de couverture de livre

NeighborMAE: Exploiting Spatial Dependencies between Neighboring Earth Observation Images in Masked Autoencoders Pretraining

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zeng, Liang, Marsocci, Valerio, Zhao, Wufan, Nascetti, Andrea, Vergauwen, Maarten
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?
par: Jia, Yuru, et autres
Publié: (2025)

MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Tasks
par: Sosa, Jose, et autres
Publié: (2025)

DailyMAE: Towards Pretraining Masked Autoencoders in One Day
par: Wu, Jiantao, et autres
Publié: (2024)

TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders
par: Faruk, Tanjim Bin, et autres
Publié: (2025)

PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models
par: Marsocci, Valerio, et autres
Publié: (2024)

COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data
par: Espinosa, Miguel, et autres
Publié: (2026)

Cross-sensor self-supervised training and alignment for remote sensing
par: Marsocci, Valerio, et autres
Publié: (2024)

R-MAE: Regions Meet Masked Autoencoders
par: Nguyen, Duy-Kien, et autres
Publié: (2023)

SenPa-MAE: Sensor Parameter Aware Masked Autoencoder for Multi-Satellite Self-Supervised Pretraining
par: Prexl, Jonathan, et autres
Publié: (2024)

SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners
par: Liang, Feng, et autres
Publié: (2022)

Synthetic Dataset Generation for Partially Observed Indoor Objects
par: Vermandere, Jelle, et autres
Publié: (2026)

Adaptive Scaling with Geometric and Visual Continuity of completed 3D objects
par: Vermandere, Jelle, et autres
Publié: (2026)

Semantic UV mapping to improve texture inpainting for indoor scenes
par: Vermandere, Jelle, et autres
Publié: (2024)

CrossVideoMAE: Self-Supervised Image-Video Representation Learning with Masked Autoencoders
par: Ahamed, Shihab Aaqil, et autres
Publié: (2025)

PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
par: Zhang, Xiangdong, et autres
Publié: (2024)

MV2MAE: Multi-View Video Masked Autoencoders
par: Shah, Ketul, et autres
Publié: (2024)

T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning
par: Wei, Weijie, et autres
Publié: (2023)

CL-MAE: Curriculum-Learned Masked Autoencoders
par: Madan, Neelu, et autres
Publié: (2023)

DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks
par: Wu, Qiangqiang, et autres
Publié: (2023)

Periodic-MAE: Periodic Video Masked Autoencoder for rPPG Estimation
par: Choi, Jiho, et autres
Publié: (2025)

MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition
par: Xiang, Peihao, et autres
Publié: (2024)

Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflection
par: Thoreau, Romain, et autres
Publié: (2025)

Efficient approximation of Earth Mover's Distance Based on Nearest Neighbor Search
par: Meng, Guangyu, et autres
Publié: (2024)

Nearest-Neighbor Density Estimation for Dependency Suppression
par: Anderson, Kathleen, et autres
Publié: (2026)

MU-MAE: Multimodal Masked Autoencoders-Based One-Shot Learning
par: Liu, Rex, et autres
Publié: (2024)

ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders
par: Hernandez, Jefferson, et autres
Publié: (2023)

Lightweight Metadata-Aware Mixture-of-Experts Masked Autoencoder for Earth Observation
par: Albughdadi, Mohanad
Publié: (2025)

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
par: Liu, Jiaming, et autres
Publié: (2023)

LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders
par: Naiman, Ilan, et autres
Publié: (2025)

$\mathsf{CSMAE~}$:~Cataract Surgical Masked Autoencoder (MAE) based Pre-training
par: Shah, Nisarg A., et autres
Publié: (2025)

Social-MAE: Social Masked Autoencoder for Multi-person Motion Representation Learning
par: Ehsanpour, Mahsa, et autres
Publié: (2024)

TerraMesh: A Planetary Mosaic of Multimodal Earth Observation Data
par: Blumenstiel, Benedikt, et autres
Publié: (2025)

How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?
par: Sosa, Jose, et autres
Publié: (2024)

i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?
par: Zhang, Kevin, et autres
Publié: (2022)

CryoMAE: Few-Shot Cryo-EM Particle Picking with Masked Autoencoders
par: Xu, Chentianye, et autres
Publié: (2024)

DuGI-MAE: Improving Infrared Mask Autoencoders via Dual-Domain Guidance
par: Xing, Yinghui, et autres
Publié: (2025)

Nearest Neighbor Classification for Classical Image Upsampling
par: Matthews, Evan, et autres
Publié: (2024)

PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder
par: Liu, Yancheng, et autres
Publié: (2026)

Adaptively Clustering Neighbor Elements for Image-Text Generation
par: Wang, Zihua, et autres
Publié: (2023)

Rethinking Patch Dependence for Masked Autoencoders
par: Fu, Letian, et autres
Publié: (2024)