Multi-Hierarchical Contrastive Spectral Fusion for Multi-View Clustering (CVPR 2026)

Bing Cai¹, Xiaoli Wang², Gui-Fu Lu³, Zechao Li¹*

¹Nanjing University of Science and Technology
²Nanjing Forestry University
³Anhui Polytechnic University

{bingcai, zechao.li}@njust.edu.cn, xiaoliwang@njfu.edu.cn, lu-guifu@ahpu.edu.cn

Abstract

Multi-view contrastive clustering has emerged as a powerful paradigm for learning comprehensive representations from heterogeneous data sources. However, prevailing approaches typically overlook the intrinsic geometric and clustering structures, rendering them structure-agnostic. In this paper, we propose a novel framework that performs Multi-Hierarchical Contrastive Spectral Fusion (MCSF) to address these limitations. MCSF integrates deep spectral embedding into the encoder to preserve local manifold structure, guiding the learned representations to be clustering-friendly. To enhance cross-view consistency, MCSF introduces a multi-hierarchical contrastive loss jointly optimizing (1) view-specific structure preservation, (2) view-consensus alignment, and (3) consensus structure refinement. This mechanism enables the construction of an accurate and semantically consistent consensus representation, effectively fusing multi-view information and uncovering authentic cluster structures. Extensive experiments on benchmarks validate the effectiveness of multi-hierarchical contrastive spectral fusion in clustering accuracy and representation quality.

Requirements

pytorch>=2.1.0 

numpy>=1.23.0

scikit-learn>=1.5.2

munkres>=1.1.4

Run

/MCSF/main.py

Note

If you have any question, please contact this e-mail: bingly@foxmail.com.

@inproceedings{cai2026multi,
  title={Multi-Hierarchical Contrastive Spectral Fusion for Multi-View Clustering},
  author={Cai, Bing and Wang, Xiaoli and Lu, Gui-Fu and Li, Zechao},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={39617--39626},
  year={2026}
}