AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Straight-Path Flow Matching for Incomplete Multi-View Clustering

Yiteng Yuan, Junyan Wang, Zheyuan Liu, Hong Jia, Lei Fan, Zhulin Tao, Lianbo Guo

ECCV 2026 · Learning theory and algorithms › Clustering · approach: Incomplete multi-view clustering · 1 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
remove cluster-level contrastive alignment loss (ablation)Straight-path FM · HandWritten tau=0.3ACC: 86.50 -> 27.75Hurt
remove entropy-based alignment loss (ablation)Straight-path FM · HandWritten tau=0.3ACC: 86.50 -> 77.20Hurt
remove flow prediction loss (ablation)Straight-path FM · HandWritten tau=0.3ACC: 86.50 -> 73.95Hurt
remove completion consistency loss (ablation)Straight-path FM · HandWritten tau=0.3ACC: 86.50 -> 76.15Hurt
add flow-matching losses to alignment-only variant (ablation)Straight-path FM · HandWritten tau=0.3ACC: 77.35 -> 86.50Improved
removing only flow-pred is worse than removing both flow losses (ablation)Straight-path FM · HandWritten tau=0.3ACC: 73.95 (w/o pred) vs 77.35 (w/o both)Mixed
replace diffusion-based DCG with straight-path flow matchingDCG · Five IMVC benchmarksACC: Synthetic3D tau=0.1 91.23 -> 94.17; CUB 82.23 -> 86.00Improved
compare at high missing rate tau=0.5Straight-path FM · FashionACC: 90.04 -> 90.09No clear effect
compare NMI at CUB tau=0.5Straight-path FM · CUBNMI: 72.21 -> 71.74Hurt
vary number of flow steps (ablation)Straight-path FM · HandWritten / Synthetic3DACCNo clear effect
vary lambda1, lambda2 (flow losses weights) (ablation)Straight-path FM · HandWritten tau=0.3ACCNo clear effect
vary lambda3, lambda4 (alignment loss weights) (ablation)Straight-path FM · HandWritten tau=0.3ACCMixed

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