AI Paper Atlas

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

The Mutex Watershed: Efficient, Parameter-Free Image Partitioning

Steffen Wolf, Constantin Pape, Alberto Bailoni, Nasim Rahaman, Anna Kreshuk, Ullrich Kothe, FredA. Hamprecht

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 57 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 Mutex Watershed instead of lifted multicut post-processing on the top leaderboard networkUNet · ISBI 2012 test leaderboardRand-Score: 0.98788 -> 0.98792Improved
use Mutex Watershed instead of MC-FULL multicut on same CNNCNN affinities · ISBI 2012 (same CNN predictions, post-processing comparison)Rand-Score: 0.98029 -> 0.98792Improved
use Mutex Watershed instead of lifted multicut on same CNNCNN affinities · ISBI 2012 (same CNN predictions, post-processing comparison)Rand-Score: 0.97990 -> 0.98792Improved
use Mutex Watershed instead of MC-FULL for runtimeCNN affinities · ISBI 2012 (same CNN predictions, post-processing comparison)runtime (s): 9415.8 -> 43.32Improved
add long-range repulsive predictions (MWS/MC-FULL/LMC versus short-range only MC-LOCAL) (ablation)multicut · ISBI 2012 (same CNN predictions, post-processing comparison)Rand-Score: 0.70990 -> 0.98029Improved
use Mutex Watershed instead of plain watershedCNN affinities · ISBI 2012 (same CNN predictions, post-processing comparison)Rand-Score: 0.63958 -> 0.98792Improved
use Mutex Watershed instead of thresholdingCNN affinities · ISBI 2012 (same CNN predictions, post-processing comparison)Rand-Score: 0.91435 -> 0.98792Improved
replace network affinities by ground-truth affinities (ablation)MWS · BSD500 test (MWS on interpolated affinities)Rand index: 0.826 -> 0.901Improved
add 62% noise to ground-truth affinities (ablation)MWS · BSD500 test (MWS on interpolated affinities)Rand index: 0.901 -> 0.897No clear effect
add 66% noise to ground-truth affinities (ablation)MWS · BSD500 test (MWS on interpolated affinities)Rand index: 0.901 -> 0.820Hurt
mix 20% ground truth into NN affinities (ablation)MWS · BSD500 test (MWS on interpolated affinities)Rand index: 0.826 -> 0.878Improved
add 57% noise to NN affinities (ablation)MWS · BSD500 test (MWS on interpolated affinities)Rand index: 0.826 -> 0.813Hurt

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