AI Paper Atlas

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

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

Jordi Pont-Tuset, Pablo Arbeláez, Jonathan T. Barron, Ferran Marqués, Jitendra Malik

TPAMI 2016 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 594 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
go from single-scale to multiscale hierarchy (combined cues)MCG segmenter · BSDS500 valFb ODS: 0.719 -> 0.725Improved
go from single-scale to multiscale hierarchy (combined cues)MCG segmenter · BSDS500 valSC ODS: 0.602 -> 0.611Improved
go from single-scale to multiscale hierarchy (combined cues)MCG segmenter · BSDS500 valVI ODS (lower is better): 1.619 -> 1.548Improved
go from single-scale to multiscale hierarchy (Pb input)MCG segmenter · BSDS500 valFop ODS: 0.334 -> 0.350Improved
combine all cues instead of structured forests alonesingle-scale segmenter · BSDS500 valFop ODS: 0.338 -> 0.358Improved
add downsampled normalized cuts (squaring and decimation)contour globalization · BSDS500 valspeed: 20x speed-upImproved
increase number of decimation steps d beyond 2 or 3DNCuts · BSDS500accuracy and speedHurt
add alignment with strength transfer to finest superpixels (vs resizing contours only) (ablation)multiscale segmentation · BSDS500 valsegmentation quality: fails to improve over the single-scale result without itImproved
add multiscale input to contour detector (vs original resolution only) (ablation)multiscale segmentation · BSDS500 valsegmentation quality: small degradation when removedImproved
use learned combiners (SVM, logistic regression, random forests) instead of uniform weights (ablation)multiscale hierarchy · BSDS500 valsegmentation qualityNo clear effect
use greedy Pareto front strategy instead of full combination (ablation)proposal list combination · SegVOC12 train, reduced problemJi: mean loss 0.0002, max loss 0.004No clear effect
add Pareto optimization over equal distribution of proposals from four scales (ablation)MCG proposals · SegVOC12Ji: gain of 2 points at working pointImproved

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