One-Step Multi-View Clustering Based on Transition Probability

• URL: http://arxiv.org/abs/2403.01460v1
• Date: Sun, 3 Mar 2024 09:43:23 GMT
• Title: One-Step Multi-View Clustering Based on Transition Probability
• Authors: Wenhui Zhao, Quanxue Gao, Guangfei Li, Cheng Deng, Ming Yang
• Abstract summary: We introduce the One-Step Multi-View Clustering Based on Transition Probability (OSMVC-TP) Our method directly learns the transition probabilities from anchor points to categories, and calculates the transition probabilities from samples to categories. To maintain consistency in labels across different views, we apply a Schatten p-norm constraint on the tensor composed of the soft labels.
• Score: 61.841829428397034
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The large-scale multi-view clustering algorithms, based on the anchor graph, have shown promising performance and efficiency and have been extensively explored in recent years. Despite their successes, current methods lack interpretability in the clustering process and do not sufficiently consider the complementary information across different views. To address these shortcomings, we introduce the One-Step Multi-View Clustering Based on Transition Probability (OSMVC-TP). This method adopts a probabilistic approach, which leverages the anchor graph, representing the transition probabilities from samples to anchor points. Our method directly learns the transition probabilities from anchor points to categories, and calculates the transition probabilities from samples to categories, thus obtaining soft label matrices for samples and anchor points, enhancing the interpretability of clustering. Furthermore, to maintain consistency in labels across different views, we apply a Schatten p-norm constraint on the tensor composed of the soft labels. This approach effectively harnesses the complementary information among the views. Extensive experiments have confirmed the effectiveness and robustness of OSMVC-TP.

Related papers

• Interpretable Multi-View Clustering Based on Anchor Graph Tensor Factorization [64.00146569922028]
  Multi-view clustering methods based on anchor graph factorization lack adequate cluster interpretability for the decomposed matrix. We address this limitation by using non-negative tensor factorization to decompose an anchor graph tensor that combines anchor graphs from multiple views.
  arXiv  Detail & Related papers  (2024-04-01T03:23:55Z)
• Anchor-free Clustering based on Anchor Graph Factorization [17.218481911995365]
  We introduce a novel method termed Anchor-free Clustering based on Anchor Graph Factorization (AFCAGF) AFCAGF innovates in learning the anchor graph, requiring only the computation of pairwise distances between samples. We evolve the concept of the membership matrix between cluster centers and samples in FKM into an anchor graph encompassing multiple anchor points and samples.
  arXiv  Detail & Related papers  (2024-02-24T02:16:42Z)
• ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classification [16.415582577355536]
  Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture label dependencies. We propose Probabilistic Multi-label Contrastive Learning (ProbMCL), a novel framework to address these challenges.
  arXiv  Detail & Related papers  (2024-01-02T22:15:20Z)
• Multi-View Clustering via Semi-non-negative Tensor Factorization [120.87318230985653]
  We develop a novel multi-view clustering based on semi-non-negative tensor factorization (Semi-NTF) Our model directly considers the between-view relationship and exploits the between-view complementary information. In addition, we provide an optimization algorithm for the proposed method and prove mathematically that the algorithm always converges to the stationary KKT point.
  arXiv  Detail & Related papers  (2023-03-29T14:54:19Z)
• Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification [80.98291772215154]
  Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations. Recent advances accomplish this task by leveraging clustering-based pseudo labels. We propose a Neighbour Consistency guided Pseudo Label Refinement framework.
  arXiv  Detail & Related papers  (2022-11-30T09:39:57Z)
• Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning [146.11600461034746]
  Method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. We prove that the core reason for this is lack of a clustering-friendly property in the embedding space.
  arXiv  Detail & Related papers  (2022-09-27T19:04:36Z)
• LaneAF: Robust Multi-Lane Detection with Affinity Fields [9.607267724849766]
  This study presents an approach to lane detection involving the prediction of binary segmentation masks and per-pixel affinity fields. affinity fields, along with the binary masks, can then be used to cluster lane pixels horizontally and vertically into corresponding lane instances in a post-processing step. Our proposed approach performs on par with state-of-the-art approaches on the limited TuSimple benchmark, and sets a new state-of-the-art on the challenging CULane dataset.
  arXiv  Detail & Related papers  (2021-03-22T17:43:19Z)
• Provably End-to-end Label-Noise Learning without Anchor Points [118.97592870124937]
  We propose an end-to-end framework for solving label-noise learning without anchor points. Our proposed framework can identify the transition matrix if the clean class-posterior probabilities are sufficiently scattered.
  arXiv  Detail & Related papers  (2021-02-04T03:59:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.