AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Nonconvex Low-Rank Tensor Representation with Deep Priors for Multiview Subspace Clustering

Yao Fu, Dong Hu, Zhi Wang

ICML 2026 · Learning theory and algorithms › Clustering · approach: Subspace clustering

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
replace tensor nuclear norm with CTS2/3N and capped l2,2/3 error term (ablation)t-SVD-MSC · COIL20ACC: 0.7711 -> 0.9730Improved
replace tensor nuclear norm with CTS2/3N and capped l2,2/3 error term (ablation)t-SVD-MSC · BBC4ViewACC: 0.8584 -> 0.9825Improved
replace tensor nuclear norm with CTS2/3N and capped l2,2/3 error term (ablation)t-SVD-MSC · 100leavesACC: 0.9419 -> 0.9581Improved
add deep prior (FFDNet denoiser) on top of CTS2/3N model (ablation)NRDN-MvSC · COIL20ACC: 0.9730 -> 1.0000Improved
add deep prior (FFDNet denoiser) on top of CTS2/3N model (ablation)NRDN-MvSC · Flower17ACC: 0.9654 -> 0.9765Improved
add deep prior (FFDNet denoiser) on top of CTS2/3N model (ablation)NRDN-MvSC · 100leavesACC: 0.9581 -> 0.9631Improved
add deep prior (FFDNet denoiser) on top of CTS2/3N model (ablation)NRDN-MvSC · YaleACC: 0.9942 -> 1.0000Improved
use nonconvex tensor-rank surrogate instead of convex TNNMvSC methods · BBC4ViewACC: about 13.43% ACC (TLSpNM-MSC over t-SVD-MSC)Improved
use tensor-oriented rather than matrix-oriented MvSCMvSC methods · multiview clustering benchmarksclustering metricsImproved
use NRDN-MvSC under 30% salt-and-pepper noiseNRDN-MvSC vs TLSpNM · Yale (30% noise)ACC: 0.5091 -> 0.7636Improved
shuffle sample order (remove pre-sorted structure)NRDN-MvSC · YaleACC: 1.0000 -> 0.7576Hurt
shuffle sample order (remove pre-sorted structure)NRDN-MvSC · UCI-digitsACC: 1.0000 -> 0.9355Hurt

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