AI Paper Atlas

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

Masked Angle-Aware Autoencoder for Remote Sensing Images

Zhihao Li, Biao Hou, Siteng Ma, zitong wu, Xianpeng Guo, bo ren, Licheng Jiao

ECCV 2024 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 32 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
use scaling center crop instead of simple random rotation to create rotated crops (ablation)MA3E · NWPU-RESISC45 fine-tuningtop-1 accuracy: 93.82 -> 95.77Improved
add OT loss for rotated crop reconstruction (with all other components) (ablation)MA3E · DOTA1.0mAP50: 76.70 -> 77.93Improved
add OT loss on top of scaling center crop only (ablation)MA3E · NWPU-RESISC45 fine-tuningtop-1 accuracy: 95.43 -> 95.06Hurt
add all MA3E components to MAE (ablation)MAE · iSAIDmIoU: 60.96 -> 62.74Improved
add angle embedding to rotated crop (ablation)MA3E · DOTA1.0mAP50: 76.12 -> 76.41Improved
increase rotated crop side length from 96 to 128 (ablation)MA3E · DOTA1.0mAP50: 77.93 -> 76.92Hurt
use more non-overlapping rotated crops per image (ablation)MA3E · NWPU-RESISC45 fine-tuningtop-1 accuracy: 95.21 -> 94.16 (a=32, 1 vs 4 crops)Hurt
choose rotated crop position by selective search instead of random (ablation)MA3E · DOTA1.0mAP50: 77.93 -> 78.08No clear effect
widen rotation range from 45 to 90 degrees (ablation)MA3E · DOTA1.0mAP50: 77.93 -> 76.45Hurt
use block-wise masking instead of random masking (ablation)MA3E · NWPU-RESISC45 fine-tuningtop-1 accuracy: 95.77 -> 94.98Hurt
pre-train longer (300 to 1600 epochs)MA3E · DOTA1.0mAP50: 77.93 -> 79.47Improved

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