AI Paper Atlas

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

SARMAE: Masked Autoencoder for SAR Representation Learning

Danxu Liu, Di Wang, Hebaixu Wang, Haoyang Chen, Wentao Jiang, Yilin Cheng, Haonan Guo, Wei Cui, Jing Zhang

CVPR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 5 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 MAE on SAR-1M instead of ImageNet-1K (ablation)MAE ViT-B · FUSAR-SHIPaccuracy (%): 75.40 -> 82.22Improved
pretrain MAE on SAR-1M instead of ImageNet-1K (ablation)MAE ViT-B · SSDDmAP (%): 64.00 -> 64.20No clear effect
pretrain MAE on SAR-1M instead of ImageNet-1K (ablation)MAE ViT-B · AIR-PolSAR-SegmIoU (%): 60.28 -> 64.36Improved
add SARE speckle-noise denoising to SAR-1M MAE (ablation)MAE* ViT-B · FUSAR-SHIPaccuracy (%): 82.22 -> 86.80Improved
add SARE speckle-noise denoising to SAR-1M MAE (ablation)MAE* ViT-B · AIR-PolSAR-SegmIoU (%): 64.36 -> 65.15Improved
add SARE speckle-noise denoising to SAR-1M MAE (ablation)MAE* ViT-B · SSDDmAP (%): 64.20 -> 64.40No clear effect
add SARC alignment to paired optical features (frozen DINOv3) (ablation)MAE* (Add noise) ViT-B · SSDDmAP (%): 64.4 -> 68.1Improved
add SARC alignment to paired optical features (ablation)MAE* (Add noise) ViT-B · FUSAR-SHIPaccuracy (%): 86.80 -> 89.30Improved
add SARC alignment to paired optical features (ablation)MAE* (Add noise) ViT-B · AIR-PolSAR-SegmIoU (%): 65.15 -> 66.53Improved
directly finetune DINOv3 on SAR instead of SARC alignment (ablation)DINOv3 · FUSAR-SHIPaccuracy (%): 74.25 vs 89.30 (SARMAE)Hurt
scale backbone from ViT-B to ViT-LSARMAE · RSARmAP (%): 66.80 -> 72.20Improved
scale backbone from ViT-B to ViT-LSARMAE · FUSAR-SHIP (30% labels)accuracy (%): 92.92 -> 92.80No clear effect

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