Aug 2026· IEEE Transactions on Pattern Analysis and Machine Intelligence· Vol PP, pp. 1-18· 0 citations
Medicine
TL;DR
Multi-view Discrete Optimal Transport is instantiated as a cluster-level transport matching framework that first adopts semi-discrete OT to learn a global OT barycenter via aggregating semantic-geometric information from all views, and then transports samples to barycenter-anchored consensus clusters under consistency constraints on semantic assignment and geometric measure.
Abstract
Multi-view clustering (MVC) relies on consistency learning to align and fuse multi-view information for building clustering decision boundaries. However, mainstream methods adopt sample-to-sample/distribution/structure similarity smoothing for consistency alignment, which builds upon continuous cluster manifolds with semantic and geometric overlap and reliable paired priors of sample correspondences. They suffer from semantic- and instance-level view-unaligned problems inherent in the real-world data with discrete non-convex structures and unreliable cross-view correspondences. Misled by unaligned noise, they weaken discriminative semantic boundaries via similarity smoothing over false-positive pairs, and degrade discrete non-convex structures by mistakenly bridging distinct cluster manifolds via pseudo-semantic interpolation. Such consistency alignment pursues highly similar representations, distributions and structures, which deviates from the clustering logic of many-to-one partitioning as well as its learning goal for separable semantic boundaries. Guided by the many-to-one principle, we jointly formulate consistency alignment and clustering decision as a novel sample-to-cluster map, termed Multi-view Discrete Optimal Transport. Specifically, MvDOT is instantiated as a cluster-level transport matching framework that first adopts semi-discrete OT to learn a global OT barycenter via aggregating semantic-geometric information from all views, and then transports samples to barycenter-anchored consensus clusters under consistency constraints on semantic assignment and geometric measure. Even with discrete cluster manifolds and unreliable sample correspondences, MvDOT achieves cross-view consistent alignment while preserving inter-cluster semantic boundaries to uncover the underlying cluster structures. Extensive experiments show MvDOT outperforms 10 baselines with higher confidence and stronger robustness in complex MVC tasks.
This work proposes a novel deep constrained multi-view clustering framework, namely SeSCE, which encodes view embeddings into a spherical space, leveraging pairwise constraints to maximize intra-class compactness and inter-class separability and introduces a confidence-aware pseudo-constraint mining mechanism.
Jun Wang, Zhenglai Li, Chuan Tang et al.· IEEE Transactions on Pattern...· 0 citations
Results suggest that decoupled matching improves robustness to appearance-driven confusion in indoor point-cloud segmentation and propose D2M-Net, a decoupled dual-matching network that separates backbone features into geometry-oriented and semantic-oriented subspaces before prototype comparison.
Han-Bin Fang, Cheng-Long Peng, Xue-Yong Xiang et al.· The Visual Computer· 0 citations
This work proposes AMCA, an unbiased SGG framework integrating adaptive multi-prototype learning with cross-modal alignment, which achieves consistently competitive performance across multiple SGG tasks, with particularly strong improvements on the unbiased mR@K metric.
Jinhao Fan, Yuan-Hao Xi, Chuanping Hu et al.· Journal of King Saud Univers...· 0 citations
Multi-view clustering aims to discover shared semantic structures from multiple complementary data views to improve clustering performance. However, most existing methods rely on a single clustering representation for each semantic cluster, which limits the ability to model complex cluster structures and diverse patter...
Dai-Dai Zhu, Yang Zhao, Dandan Ma et al.· Proceedings of the Thirty-Fi...· 0 citations
The Dual-tOpology learning with adapTive Anchors (DOTA) is proposed, which not only learns the sample-anchor relationship but also preserves the topology structure among anchors, significantly enhancing the discriminability of learned representation while preserving the underlying data manifold.
Cheng-Long Zhang, Chao Zhang, Jun-Hao Zhang et al.· Proceedings of the Thirty-Fi...· 0 citations
Multi-view Clustering via Manifold Decomposition is proposed, which directly infers cluster labels from multi-view data without explicit similarity graph construction or anchor selection, and reformulates multi-view clustering as a unified multi-view regression problem, where cluster labels are optimized as model varia...
Xiao-Wei Zhao, Xin-Yue Kou, Yan Chen et al.· Proceedings of the Thirty-Fi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.