AI Paper Atlas

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

MultiSeg: Semantically Meaningful, Scale-Diverse Segmentations From Minimal User Input

Jun Hao Liew, Scott Cohen, Brian Price, Long Mai, Sim-Heng Ong, Jiashi Feng

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 41 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 scale-prior branches (scale diversity) instead of ranked diversity loss (ablation)MultiSeg · Fashionista (object parts)#Total interactions: 12.01 -> 8.61Improved
add scale priors instead of ranked diversity loss (fewer proposal selections) (ablation)MultiSeg · Fashionista (object parts)#Select: 3.87 -> 0.96Improved
add scale priors instead of ranked diversity loss in the user study (ablation)MultiSeg · User study (50 images, 5 participants)#Total interactions: 4.38 -> 3.54Improved
add scale priors instead of ranked diversity loss in the user study (time) (ablation)MultiSeg · User study (50 images, 5 participants)Time (s): 9.47 -> 7.55Improved
use MultiSeg instead of single-output DIOS in the user studyDeepLabv3+ interactive segmentation · User study (50 images, 5 participants)Time (s): 8.84 -> 7.55Improved
use MultiSeg instead of single-output DIOS on object partsDeepLabv3+ interactive segmentation · Fashionista (object parts)#Total interactions: 9.13 -> 8.61Improved
retrain DIOS with the same DeepLabv3+ backboneDIOS · PASCAL VOC val (85% IoU)clicks to 85% IoU: 6.88 -> 3.51Improved
use MultiSeg instead of backbone-matched DIOS for single objectsDeepLabv3+ interactive segmentation · PASCAL VOC val (85% IoU)clicks to 85% IoU: 3.51 -> 3.88No clear effect
use MultiSeg instead of backbone-matched DIOS on BerkeleyDeepLabv3+ interactive segmentation · Berkeley (90% IoU)clicks to 90% IoU: 4.31 -> 4.00Improved
add synthesized diverse training samples (versus MultiSeg-SingleGt) (ablation)MultiSeg · PASCAL VOC val (m-diversity score)m-diversity scoreImproved
define output branches by scale instead of ranked diversity loss (ablation)MultiSeg · PASCAL VOC val (m-diversity score)m-diversity scoreImproved

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