AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning

Wenhui Diao, Haichen Yu, Kootak Kang, Tong Ling, Di Liu, Yingchao Feng, Hanbo Bi, Libo Ren, Xuexue Li, Yongqiang Mao, Xian Sun

TPAMI 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Efficient ViT adaptation · 17 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
add FE-MSA and MIM pre-training on aerial data (RingMo-Aerial MIM vs RingMo) (ablation)RingMo-Aerial · UAVid segmentation (UperNet)mIoU: 61.9 -> 65.8Improved
add affine-transformation contrastive learning after MIM pre-training (ablation)RingMo-Aerial · UAVid segmentation (UperNet)mIoU: 65.8 -> 66.4Improved
add affine-transformation contrastive learning after MIM pre-training (ablation)RingMo-Aerial · VisDrone-DET (Cascade RCNN)mAP: 30.5 -> 31.1Improved
add contrastive learning pre-training when fine-tuning with ARS-Adapter (ablation)RingMo-Aerial + ARS-Adapter · VisDrone-DETmAP: 25.3 -> 31.0Improved
add contrastive learning pre-training when fine-tuning with ARS-Adapter (ablation)RingMo-Aerial + ARS-Adapter · UAVidmIoU: 62.9 -> 64.4Improved
use ARS-Adapter instead of Adapter for parameter-efficient fine-tuning (ablation)RingMo-Aerial · UAVidmIoU: 57.7 -> 64.4Improved
use ARS-Adapter instead of AdaptFormer (ablation)RingMo-Aerial · UAVidmIoU: 62.1 -> 64.4Improved
use ARS-Adapter (0.41% params) instead of full fine-tuning (ablation)RingMo-Aerial · VisDrone-DETmAP: 31.1 -> 31.0No clear effect
raise pre-training mask ratio from 0.6 to 0.8 (ablation)RingMo-Aerial · DroneVehicle RGB+IRmAP_s: 0.228 -> 0.235Mixed
change mask ratio from 0.6 to 0.7 (ablation)RingMo-Aerial · UAVidmIoU: 68.70 -> 67.72Hurt
place depthwise conv before attention rather than after FFN (ablation)FE-MSA · DroneVehicle RGB+IRmAP: 0.485 -> 0.492Improved
use depthwise kernel size 7 instead of 3 (ablation)FE-MSA · DroneVehicle RGB+IRmAP: 0.485 -> 0.492Improved

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