AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation

Shiqi Huang, Shuting He, Huaiyuan Qin, Bihan Wen

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 8 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 Region-Aware Integration (RAI) (ablation)SCORE · OV RS instance seg (train iSAID, average)mAP: 33.25 -> 36.91Improved
add Global Context Adaptation (GCA) (ablation)SCORE · OV RS instance seg (train iSAID, average)mAP: 33.25 -> 36.67Improved
add both RAI and GCA (ablation)SCORE · OV RS instance seg (train iSAID, average)mAP: 33.25 -> 38.68Improved
add both RAI and GCA (ablation)SCORE · OV RS instance seg (train SIOR, average)mAP: 28.36 -> 32.59Improved
use RemoteCLIP instead of general CLIP for scene context (ablation)SCORE · OV RS instance seg (train iSAID)mAP: 64.03 -> 67.59Improved
use regional context instead of [CLS] token in RAI (ablation)SCORE · OV RS instance seg (train iSAID)mAP: 67.06 -> 67.59Improved
use regional context instead of patch embeddings in RAI (ablation)SCORE · OV RS instance seg (train iSAID)mAP: 66.14 -> 67.59Improved
inject global context by MHA instead of addition (ablation)SCORE GCA · OV RS instance seg (train iSAID)mAP: 65.72 -> 67.59Improved
inject global context by MHA instead of concatenation (ablation)SCORE GCA · OV RS instance seg (train iSAID)mAP: 47.53 -> 67.59Improved
use general CLIP instead of RemoteCLIP for out-vocabulary classification (ablation)SCORE · OV RS instance seg (train iSAID)mAP: 66.05 -> 67.59Improved
use SCORE instead of FC-CLIP baselineFC-CLIP · OV RS instance seg (train iSAID, average)mAP: 33.24 -> 38.68Improved
apply SCORE to semantic segmentation instead of GSNetGSNet · OV RS semantic seg (LandDiscover50K)mIoU: 28.63 -> 29.76Mixed

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