Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning

• URL: http://arxiv.org/abs/2411.03978v1
• Date: Wed, 06 Nov 2024 15:14:27 GMT
• Title: Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning
• Authors: Jiawei Yao, Qi Qian, Juhua Hu,
• Abstract summary: We introduce Multi-Sub, a novel end-to-end multiple clustering approach that incorporates a multi-modal subspace proxy learning framework. Our method consistently outperforms existing baselines across a broad set of datasets in visual multiple clustering tasks.
• Score: 8.447067012487866
• License:
• Abstract: Multiple clustering aims to discover various latent structures of data from different aspects. Deep multiple clustering methods have achieved remarkable performance by exploiting complex patterns and relationships in data. However, existing works struggle to flexibly adapt to diverse user-specific needs in data grouping, which may require manual understanding of each clustering. To address these limitations, we introduce Multi-Sub, a novel end-to-end multiple clustering approach that incorporates a multi-modal subspace proxy learning framework in this work. Utilizing the synergistic capabilities of CLIP and GPT-4, Multi-Sub aligns textual prompts expressing user preferences with their corresponding visual representations. This is achieved by automatically generating proxy words from large language models that act as subspace bases, thus allowing for the customized representation of data in terms specific to the user's interests. Our method consistently outperforms existing baselines across a broad set of datasets in visual multiple clustering tasks. Our code is available at https://github.com/Alexander-Yao/Multi-Sub.

Related papers

• Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering [8.447067012487866]
  Multi-MaP is a novel method employing a multi-modal proxy learning process. It captures a user's interest via a keyword but also facilitates identifying relevant clusterings. Our experiments show that Multi-MaP consistently outperforms state-of-the-art methods in all benchmark multi-clustering vision tasks.
  arXiv  Detail & Related papers  (2024-04-24T05:20:42Z)
• Federated Deep Multi-View Clustering with Global Self-Supervision [51.639891178519136]
  Federated multi-view clustering has the potential to learn a global clustering model from data distributed across multiple devices. In this setting, label information is unknown and data privacy must be preserved. We propose a novel federated deep multi-view clustering method that can mine complementary cluster structures from multiple clients.
  arXiv  Detail & Related papers  (2023-09-24T17:07:01Z)
• Preserving Modality Structure Improves Multi-Modal Learning [64.10085674834252]
  Self-supervised learning on large-scale multi-modal datasets allows learning semantically meaningful embeddings without relying on human annotations. These methods often struggle to generalize well on out-of-domain data as they ignore the semantic structure present in modality-specific embeddings. We propose a novel Semantic-Structure-Preserving Consistency approach to improve generalizability by preserving the modality-specific relationships in the joint embedding space.
  arXiv  Detail & Related papers  (2023-08-24T20:46:48Z)
• Large Language Models Enable Few-Shot Clustering [88.06276828752553]
  We show that large language models can amplify an expert's guidance to enable query-efficient, few-shot semi-supervised text clustering. We find incorporating LLMs in the first two stages can routinely provide significant improvements in cluster quality.
  arXiv  Detail & Related papers  (2023-07-02T09:17:11Z)
• Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation [65.268245109828]
  Online deep clustering refers to the joint use of a feature extraction network and a clustering model to assign cluster labels to each new data point or batch as it is processed. While faster and more versatile than offline methods, online clustering can easily reach the collapsed solution where the encoder maps all inputs to the same point and all are put into a single cluster. We propose a method that does not require data augmentation, and that, differently from existing methods, regularizes the hard assignments.
  arXiv  Detail & Related papers  (2023-03-29T08:23:26Z)
• Multi-view Semantic Consistency based Information Bottleneck for Clustering [13.589996737740208]
  We introduce a novel Multi-view Semantic Consistency based Information Bottleneck for clustering (MSCIB) MSCIB pursues semantic consistency to improve the learning process of information bottleneck for different views. It conducts the alignment operation of multiple views in the semantic space and jointly achieves the valuable consistent information of multi-view data.
  arXiv  Detail & Related papers  (2023-02-28T02:01:58Z)
• Fast Multi-view Clustering via Ensembles: Towards Scalability, Superiority, and Simplicity [63.85428043085567]
  We propose a fast multi-view clustering via ensembles (FastMICE) approach. The concept of random view groups is presented to capture the versatile view-wise relationships. FastMICE has almost linear time and space complexity, and is free of dataset-specific tuning.
  arXiv  Detail & Related papers  (2022-03-22T09:51:24Z)
• Smoothed Multi-View Subspace Clustering [14.77544837600836]
  We propose a novel multi-view clustering method named smoothed multi-view subspace clustering (SMVSC) It employs a novel technique, i.e., graph filtering, to obtain a smooth representation for each view. Experiments on benchmark datasets validate the superiority of our approach.
  arXiv  Detail & Related papers  (2021-06-18T02:24:19Z)
• Deep Incomplete Multi-View Multiple Clusterings [41.43164409639238]
  We introduce a deep incomplete multi-view multiple clusterings framework, which achieves the completion of data view and multiple shared representations simultaneously. Experiments on benchmark datasets confirm that DiMVMC outperforms the state-of-the-art competitors in generating multiple clusterings with high diversity and quality.
  arXiv  Detail & Related papers  (2020-10-02T08:01:24Z)
• Joint Featurewise Weighting and Lobal Structure Learning for Multi-view Subspace Clustering [3.093890460224435]
  Multi-view clustering integrates multiple feature sets, which reveal distinct aspects of the data and provide complementary information to each other. Most existing multi-view clustering methods only aim to explore the consistency of all views while ignoring the local structure of each view. We propose a novel multi-view subspace clustering method via simultaneously assigning weights for different features and capturing local information of data in view-specific self-representation feature spaces.
  arXiv  Detail & Related papers  (2020-07-25T01:57:57Z)
• Multi-view Deep Subspace Clustering Networks [64.29227045376359]
  Multi-view subspace clustering aims to discover the inherent structure of data by fusing multiple views of complementary information. We propose the Multi-view Deep Subspace Clustering Networks (MvDSCN), which learns a multi-view self-representation matrix in an end-to-end manner. The MvDSCN unifies multiple backbones to boost clustering performance and avoid the need for model selection.
  arXiv  Detail & Related papers  (2019-08-06T06:44:43Z)

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.