Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Xiaodong, Huang, Jing, Liang, Kevin J
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.05462
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908636468477952
author Wang, Xiaodong
Huang, Jing
Liang, Kevin J
author_facet Wang, Xiaodong
Huang, Jing
Liang, Kevin J
contents Recent studies have demonstrated the effectiveness of clustering-based approaches for self-supervised and unsupervised learning. However, the application of clustering is often heuristic, and the optimal methodology remains unclear. In this work, we establish connections between these unsupervised clustering methods and classical mixture models from statistics. Through this framework, we demonstrate significant enhancements to these clustering methods, leading to the development of a novel model named SiamMM. Our method attains state-of-the-art performance across various self-supervised learning benchmarks. Inspection of the learned clusters reveals a strong resemblance to unseen ground truth labels, uncovering potential instances of mislabeling.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05462
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SiamMM: A Mixture Model Perspective on Deep Unsupervised Learning
Wang, Xiaodong
Huang, Jing
Liang, Kevin J
Machine Learning
Computer Vision and Pattern Recognition
Recent studies have demonstrated the effectiveness of clustering-based approaches for self-supervised and unsupervised learning. However, the application of clustering is often heuristic, and the optimal methodology remains unclear. In this work, we establish connections between these unsupervised clustering methods and classical mixture models from statistics. Through this framework, we demonstrate significant enhancements to these clustering methods, leading to the development of a novel model named SiamMM. Our method attains state-of-the-art performance across various self-supervised learning benchmarks. Inspection of the learned clusters reveals a strong resemblance to unseen ground truth labels, uncovering potential instances of mislabeling.
title SiamMM: A Mixture Model Perspective on Deep Unsupervised Learning
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.05462