AI Paper Atlas

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

Prompt-Free Unknown Label Generation for Open World Detection in Remote Sensing

Abdullah Azeem, Ruisheng Wang, Qingquan Li, Abubakar Siddique

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection

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 DHGA hierarchical graph attention to the baseline (ablation)Deformable DETR + CLIP baseline with ORE-style unknown detection · DOTA-v2 Task 1Unknown Recall: 20.5 -> 28.0Improved
add DHGA hierarchical graph attention to the baseline (ablation)Deformable DETR + CLIP baseline · DOTA-v2 Task 1Known mAP: 44.7 -> 48.9Improved
add Scene Context Token on top of DHGA (ablation)HSGDet · DOTA-v2 Task 1Unknown Recall: 28.0 -> 33.8Improved
add CR2T on top of DHGA and SCT (ablation)HSGDet · DOTA-v2 Task 1Unknown Recall: 33.8 -> 41.2Improved
add CR2T on top of DHGA and SCT (ablation)HSGDet · DOTA-v2 Task 1Wilderness Impact: 08.4 -> 05.8Improved
add hierarchical parent to CR2T inputs (ablation)CR2T · DOTA-v2 Task 1Unknown Recall: 37.4 -> 38.6Improved
add sibling context to CR2T inputs (ablation)CR2T · DOTA-v2 Task 1Text Alignment: 0.63 -> 0.66Improved
use full CR2T (visual, scene context, parent) instead of visual-only (ablation)CR2T · DOTA-v2 Task 1Text Alignment: 0.56 -> 0.79Improved
raise masked pseudo-unknown class ratio from 10% to 30% (ablation)CR2T training · DOTA-v2 Task 1Unknown Recall: 39.2 -> 41.2Improved
use HSGDet instead of prior OWOD methods on COCO across incremental tasksHSGDet · COCO Task 4Known mAP: 81.2 vs OW-OVD 64.8Improved
use HSGDet instead of SkySense-O on remote sensing benchmarksHSGDet · FAIR1M and DIORKnown mAP / Unknown Recall: +6.6 and +6.4 K-mAP, +9.9 and +9.2 U-RImproved

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