用可微聚类提升半监督学习，训练更简单效果更好
Supercm: Revisiting Clustering for Semi-Supervised Learning
- 引入可微聚类模块，显式利用数据聚类特性
- 仅用标注数据引导聚类中心，实现端到端训练
- 兼容其他半监督方法，适合想简化流程的研究者
近年来半监督学习（SSL）的发展主要集中在一致性正则化或熵最小化方法，常导致训练策略复杂。本文提出一种新方法，通过扩展最近提出的可微聚类模块，显式引入SSL中的聚类假设。利用标注数据引导聚类中心，实现简单且端到端可训练的深度半监督学习框架。实验表明，该模型优于纯监督基线，并可与其它SSL方法结合进一步提升性能。
原文摘要 · Abstract (English)
The development of semi-supervised learning (SSL) has in recent years largely focused on the development of new consistency regularization or entropy minimization approaches, often resulting in models with complex training strategies to obtain the desired results. In this work, we instead propose a novel approach that explicitly incorporates the underlying clustering assumption in SSL through extending a recently proposed differentiable clustering module. Leveraging annotated data to guide the cluster centroids results in a simple end-to-end trainable deep SSL approach. We demonstrate that the proposed model improves the performance over the supervised-only baseline and show that our framework can be used in conjunction with other SSL methods to further boost their performance.
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。