用扩散模型生成多样聚类，提升无监督分类效果
Clustering via Self-Supervised Diffusion
- 教师-学生框架：通过扩散采样生成多样聚类，学生优化为稳定预测
- 在多个挑战性数据集上达到顶尖聚类性能，显著提升鲁棒性
- 适合需要高精度无监督聚类的视觉任务，如图像分组与结构发现
扩散模型虽在生成任务中表现优异，但尚未用于聚类。本文提出基于扩散的聚类框架CLUDI，结合预训练视觉变换器特征与扩散模型的生成能力，实现鲁棒且精准的聚类。CLUDI采用教师-学生范式：教师通过基于随机扩散的采样生成多样化的聚类分配，学生将其优化为稳定预测。这种随机性作为新型数据增强策略，使CLUDI能揭示高维数据中的复杂结构。在多个挑战性数据集上的大量评估表明，CLUDI在无监督分类中达到当前最优性能，树立了聚类鲁棒性和对复杂数据分布适应性的新基准。代码已开源。
原文摘要 · Abstract (English)
Diffusion models, widely recognized for their success in generative tasks, have not yet been applied to clustering. We introduce Clustering via Diffusion (CLUDI), a self-supervised framework that combines the generative power of diffusion models with pre-trained Vision Transformer features to achieve robust and accurate clustering. CLUDI is trained via a teacher-student paradigm: the teacher uses stochastic diffusion-based sampling to produce diverse cluster assignments, which the student refines into stable predictions. This stochasticity acts as a novel data augmentation strategy, enabling CLUDI to uncover intricate structures in high-dimensional data. Extensive evaluations on challenging datasets demonstrate that CLUDI achieves state-of-the-art performance in unsupervised classification, setting new benchmarks in clustering robustness and adaptability to complex data distributions. Our code is available at https://github.com/BGU-CS-VIL/CLUDI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。