AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Simultaneous Clustering and Model Selection for Tensor Affinities

Zhuwen Li, Shuoguang Yang, Loong-Fah Cheong, Kim-Chuan Toh

CVPR 2016 · Learning theory and algorithms › Clustering · approach: Subspace clustering · 7 citations (OpenAlex)

Check 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
apply SCAMSTA directly to the higher-order affinity tensor instead of using projected-graph baselinesYork Urban Dataset, pre-selected · York Urban Dataset, pre-selectedF1-measure: 0.8884 ± 0.1083 -> 0.9426 ± 0.0739Improved
use the stochastic ADMM slice formulation (ablation)SCAMSTA · York Urban Dataset, pre-selectedF1-measure: 0.9426 ± 0.0739 -> 0.9274 ± 0.0793Hurt
apply SCAMSTA directly to the higher-order affinity tensor instead of using projected-graph baselinesYork Urban Dataset, detected · York Urban Dataset, detectedF1-measure: 0.7993 ± 0.1966 -> 0.8273 ± 0.1760Improved
use the stochastic ADMM slice formulation (ablation)SCAMSTA · York Urban Dataset, detectedF1-measure: 0.8273 ± 0.1760 -> 0.8035 ± 0.1938Hurt
use the stochastic ADMM slice formulation for scalable higher-order clusteringSCAMSTA · AdelaideRMFF1-measure: 0.7827± 0.1925 -> 0.8418 ± 0.1071Improved
use higher-order affinities directly rather than projecting them to pairwise affinitiesSCAMSTA-SADMM · AdelaideRMFF1-measure: 0.7827± 0.1925 -> 0.8418 ± 0.1071Improved

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