Clustering via Self-Supervised Diffusion
Clustering via Self-Supervised Diffusion
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.
Roy Uziel、Irit Chelly、Oren Freifeld、Ari Pakman
计算技术、计算机技术
Roy Uziel,Irit Chelly,Oren Freifeld,Ari Pakman.Clustering via Self-Supervised Diffusion[EB/OL].(2025-07-06)[2025-07-16].https://arxiv.org/abs/2507.04283.点此复制
评论