atlas

Research map / Learning theory and algorithms / Clustering

Superpixels and Polygons Using Simple Non-Iterative Clustering

CVPR 2017 · Learning theory and algorithms › Clustering · approach: Subspace clustering · 496 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 SLIC's iterative clustering with priority-queue pixel assignment and online centroid updatesSNIC · Berkeley 300F-measureHelped
Replace SLIC's iterative clustering with priority-queue pixel assignment and online centroid updatesSNIC · Berkeley 300boundary recall and precisionHelped
Enforce connectivity during clustering rather than as a post-processing stepSNIC · Berkeley 300memory consumptionHelped
Use SNIC superpixel boundaries as the basis for polygon generationSNICPOLY · Berkeley 300CUSEHelped
Use SNIC superpixel boundaries as the basis for polygon generationSNICPOLY · Berkeley 300F-measureHelped
Use SNIC superpixel boundaries as the basis for polygon generationSNICPOLY · Berkeley 300runtimeHelped
Restrict pixel visits to candidates connected to a growing clusterSNIC · Berkeley 300runtimeHelped

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