AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

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

Liang Zeng, Valerio Marsocci, Wufan Zhao, Andrea Nascetti, Maarten Vergauwen

CVPR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
pretrain with NeighborMAE instead of MAEMAE ViT-L pretrained on fMoW · fMoW classification (linear probing)accuracy: 66.8 -> 68.8Improved
pretrain with NeighborMAE instead of MAEMAE ViT-L pretrained on fMoW · Five-Billion-Pixels segmentation (fine-tuned)mIoU: +2.7% mIoUImproved
enlarge input area instead of using neighbors (ablation)MAE ViT-B pretrained on fMoW · fMoW classification (frozen)accuracy: 58.0 -> 58.2No clear effect
sample uni-temporal neighboring images instead of base input (ablation)MAE ViT-B pretrained on fMoW · fMoW classification (frozen)accuracy: 58.0 -> 58.7Improved
use multi-temporal neighbors instead of uni-temporal neighbors (ablation)NeighborMAE ViT-B pretrained on fMoW · fMoW classification (frozen)accuracy: 58.7 -> 61.7Improved
use multi-temporal neighbors instead of uni-temporal neighbors (ablation)NeighborMAE ViT-B pretrained on Satellogic · fMoW classification (frozen)accuracy: 50.1 -> 52.4Improved
use co-located multi-temporal images instead of neighbors (ablation)NeighborMAE ViT-B pretrained on fMoW · fMoW classification (frozen)accuracy: 58.7 -> 58.2No clear effect
use dynamic mask ratio (0.75 to 0.85) instead of constant 0.75 (ablation)NeighborMAE ViT-B pretrained on fMoW · fMoW classification (frozen)accuracy: 61.0 -> 61.7Improved
raise upper bound of mask ratio from 0.85 to 0.90 (ablation)NeighborMAE ViT-B pretrained on fMoW · fMoW classification (frozen)accuracy: 61.7 -> 61.4Hurt
use input-visibility loss weighting instead of full reconstruction loss (ablation)NeighborMAE ViT-B pretrained on fMoW · fMoW classification (frozen)accuracy: 58.6 -> 61.7Improved
use visibility-based loss weight for cross-visible pixels instead of weight 1 (ablation)NeighborMAE ViT-B pretrained on fMoW · fMoW classification (frozen)accuracy: 61.6 -> 61.7No clear effect
use visibility-based loss weight for cross-visible pixels instead of weight 1 (ablation)NeighborMAE ViT-B pretrained on Satellogic · fMoW classification (frozen)accuracy: 51.8 -> 52.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy