AI Paper Atlas

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

From Visual Primitives to Semantic Masks: Fine-Grained Visual-Linguistic Alignment for Open-Vocabulary Remote Sensing Image Segmentation

Yuchen Deng, Yang Xu, Zhihui Wei, Zebin Wu

ECCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 0 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 dynamic prototype injection (DPI) (ablation)SAM 3 · FG-OVSSRS Bench: CloudmIoU (%): 29.56 -> 29.68Improved
add DPI (ablation)SAM 3 · FG-OVSSRS Bench: YRCCmIoU (%): 52.66 -> 55.25Improved
add DPI (ablation)SAM 3 · FG-OVSSRS Bench: RescuemIoU (%): 35.76 -> 36.67Improved
add static prototype injection (SPI) to DPI (ablation)SANO3 · FG-OVSSRS Bench: CloudmIoU (%): 29.68 -> 30.11Improved
add SPI to DPI (ablation)SANO3 · FG-OVSSRS Bench: YRCCmIoU (%): 55.25 -> 56.46Improved
add SPI to DPI (ablation)SANO3 · FG-OVSSRS Bench: RescuemIoU (%): 36.67 -> 36.82Improved
add iterative information-gain visual prompting (IGVP) (ablation)SANO3 · FG-OVSSRS Bench: CloudmIoU (%): 30.11 -> 30.70Improved
add IGVP (ablation)SANO3 · FG-OVSSRS Bench: YRCCmIoU (%): 56.46 -> 57.78Improved
add IGVP (ablation)SANO3 · FG-OVSSRS Bench: RescuemIoU (%): 36.82 -> 36.84Improved
use VARA alignment instead of max cosine similarity matching (ablation)SANO3 · FG-OVSSRS Bench: CloudmIoU (%): 30.30 -> 30.70Improved
use VARA instead of max cosine similarity (ablation)SANO3 · FG-OVSSRS Bench: YRCCmIoU (%): 57.11 -> 57.78Improved
use DINOv2 instead of MAE as VFM (ablation)SANO3 · FG-OVSSRS Bench: YRCCmIoU (%): 58.64 -> 57.78Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 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