AI Paper Atlas

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

Predicting How to Distribute Work Between Algorithms and Humans to Segment an Image Batch

Danna Gurari, Yinan Zhao, Suyog Dutt Jain, Margrit Betke, Kristen Lorraine Grauman

IJCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 5 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
use the proposed quality predictor instead of CPMCquality predictor · BU-BIL (cross-dataset)Pearson CC: 0.18 -> 0.63Improved
train on a single dataset instead of cross-datasetquality predictor · all four datasetsPearson CC: ~0.60 -> ~0.85Improved
add mask-based features to intensity-only features (ablation)quality predictor · BU-BIL (cross-dataset)Pearson CC: -0.10 -> 0.63Improved
add intensity features to mask-only features (ablation)quality predictor · Weizmann (cross-dataset)Pearson CC: 0.65 -> 0.61Hurt
add intensity features to mask-only features (ablation)quality predictor · IIS (single-dataset)Pearson CC: 0.73 -> 0.83Improved
add intensity features to mask-only features (ablation)quality predictor · BU-BIL (single-dataset)Pearson CC: 0.88 -> 0.87Hurt
predict best of 14 algorithm segmentations instead of Rectangle initializationPTP initialization · All images, Lankton level set, 0% humansegmentation quality: 31 percentage pointsImproved
predict best of 14 algorithm segmentations instead of Rectangle initializationPTP initialization · All images, GrabCut, 0% humansegmentation quality: 15 percentage pointsImproved
use non-linear regression trees over 14 options instead of Linear model over 8 optionsPTP initialization · Weizmann, Lankton level setsegmentation quality: 14 percentage pointsImproved
use predicted initialization instead of Rectangle with GrabCutPTP initialization · IIS, GrabCutsegmentation quality: approximately two percentage pointsHurt
add refinement algorithm to coarse segmentation (ablation)PTP initialization · All images, Lankton level setsegmentation quality: over 20 percentage pointsImproved
add GrabCut refinement to coarse segmentation (ablation)PTP initialization · All images, GrabCutsegmentation quality: 26 percentage improvementImproved

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