AI Paper Atlas

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

Dominant Sets for “Constrained” Image Segmentation

Eyasu Zemene, Leulseged Tesfaye Alemu, Marcello Pelillo

TPAMI 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 22 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
replace Constrained Random Walker with constrained dominant sets (self-tuning sigma)Constrained Random Walker · GrabCut (scribbles)error rate (%): 4.1 -> 3.57Improved
select sigma per database instead of self-tuningCDS · GrabCut (scribbles)error rate (%): 3.57 -> 3.80Hurt
select sigma per image (oracle upper bound) instead of self-tuning (ablation)CDS · GrabCut (scribbles)error rate (%): 3.57 -> 2.72Improved
replace MILCut-Struct bounding-box method with CDS (self-tuning)MILCut-Struct · BerkeleyJaccard index: 84 -> 93Improved
select sigma per image (oracle) instead of self-tuning (ablation)CDS · BerkeleyJaccard index: 93 -> 95Improved
increase bounding-box looseness from L=0 to L=600 for GrabCutGrabCut · GrabCut loose boxeserror rate (%): 7.4 -> 13.7Hurt
increase bounding-box looseness from L=0 to L=600 for CDS single sigmaCDS Single Sigma · GrabCut loose boxeserror rate (%): 7.48 -> 6.29Improved
replace LooseCut with CDS single sigma at L=600LooseCut · GrabCut loose boxeserror rate (%): 6.8 -> 6.29Improved
replace LooseCut with CDS self-tuning at L=0LooseCut · GrabCut loose boxeserror rate (%): 7.9 -> 7.54Improved
replace BNC with constrained dominant sets for interactive co-segmentationBNC · Image pairsF-measure: 0.6564 -> 0.7140Improved
replace BNC with constrained dominant sets for interactive co-segmentationBNC · Image pairsrecall: 0.8512 -> 0.8208No clear effect
increase share of erroneous scribbles from 0% to 100%CDS · GrabCut synthetic scribbleserror rateNo clear effect

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