AI Paper Atlas

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

Improving Target Presence and Plurality Recognition for Generalized Referring Image Segmentation

Namyup Kim, Jinsung Lee, Suha Kwak

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring 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 target query for presence classification (ablation)generalized RIS model · gRefCOCO valgIoU: 62.39 -> 64.93Improved
add target query for presence classification (ablation)generalized RIS model · gRefCOCO valcIoU: 59.62 -> 63.86Improved
add plurality classification head on target query (ablation)generalized RIS model with target query · gRefCOCO valgIoU: 64.93 -> 66.11Improved
add no-target data augmentation (ablation)target query plus plurality model · gRefCOCO valN-acc: 57.42 -> 71.28Improved
add no-target data augmentation (ablation)target query plus plurality model · gRefCOCO valcIoU: 65.05 -> 63.61Hurt
add multi-target data augmentation on top of no-target augmentation (ablation)target query plus plurality model · gRefCOCO valcIoU: 63.61 -> 66.61Improved
add multi-target data augmentation on top of no-target augmentation (ablation)target query plurality model · gRefCOCO valgIoU: 69.24 -> 71.32Improved
use proposed architecture instead of ReLAgeneralized RIS · gRefCOCO valN-acc: 56.37 -> 72.27Improved
use proposed model instead of GSVA (LMM-based)generalized RIS · gRefCOCO valgIoU: 66.47 -> 71.32Improved
use proposed model instead of GSVA on testBgeneralized RIS · gRefCOCO testBgIoU: 62.23 -> 62.24No clear effect
attach ReLA's presence head (ablation)ReLA · gRefCOCO valgIoU: +0.27%pNo clear effect
replace ReLA presence prediction with ground-truth presence labels (ablation)ReLA · gRefCOCO valgIoU: +18.04%pImproved

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