AI Paper Atlas

Research map / Detection and segmentation / CNN features

Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling

Fengxiang Wang, Hongzhen Wang, Di Wang, Zonghao Guo, Zhenyu Zhong, Long Lan, Wenjing Yang, Jing Zhang

ICCV 2025 · Detection and segmentation › CNN features · approach: Plain and high-resolution ViTs · 31 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
replace MAE with SelectiveMAE (HOG selection, PSTS, partial reconstruction)ViT-B pre-training · OpticalRS-13M pre-trainingdata throughput per minute: 264k -> 556kImproved
replace MAE with SelectiveMAEViT-B, 1M images · Pre-training efficiencytraining time (h): 51 -> 24Improved
replace MAE with SelectiveMAEViT-L, 1M images · Pre-training efficiencytraining time (h): 57 -> 25Improved
replace MAE with SelectiveMAEViT-B, 1M images · Pre-training efficiencyGPU memory (MB): 17628 -> 9570Improved
replace MAE with SelectiveMAEViT-B · AID (TR=20%)overall accuracy: 96.58 -> 96.90Improved
replace MAE with SelectiveMAEViT-B · SpaceNetv1mF1: 79.41 -> 79.50No clear effect
scale SelectiveMAE from ViT-B to ViT-L (ablation)SelectiveMAE · DIOR-RmAP50: 67.69 -> 71.75Improved
add HOG selection instead of Swin-B feature clustering (ablation)SelectiveMAE · AID (TR=20%, MillionAID)overall accuracy: 93.21 -> 93.17No clear effect
select tokens by HOG instead of Adamae sampler (ablation)SelectiveMAE · AID (TR=20%, MillionAID)overall accuracy: 88.78 -> 93.17Improved
reconstruct HOG-selected patches instead of random patches (ablation)partial reconstruction · AID (TR=20%, MillionAID)overall accuracy: 94.1 -> 94.8Improved
use near-far-random selection in PSTS instead of far-near-random (ablation)SelectiveMAE · AID (TR=20%, MillionAID)overall accuracy: 90.12 -> 93.17Improved
pre-train on OpticalRS-13M subset instead of MillionAID (ablation)MAE ViT-B · AID (TR=20%, 1M images)overall accuracy: 94.92 -> 96.26Improved

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