通过视图与聚类的一致性分配进行表示学习
Representation Learning via Consistent Assignment of Views to Clusters
AI总结：
本文提出无监督视觉表示学习方法CARL，结合自监督对比学习与深度聚类，通过在线学习通用原型并利用梯度下降解决聚类分配问题，在多项表示学习基准中取得领先。
摘要：
我们引入了用于表示学习的一致性分配（CARL），这是一种无监督学习方法，通过结合自监督对比学习和深度聚类的思想来学习视觉表示。从聚类视角看待对比学习，CARL通过学习一组通用原型作为能量锚点，强制将给定图像的不同视图分配到同一原型，从而学习无监督表示。与当代结合对比学习与深度聚类的工作不同，CARL提出以在线方式学习这组通用原型，使用梯度下降，无需使用不可微算法或K-Means来解决聚类分配问题。CARL在许多表示学习基准中超越了竞争对手，包括线性评估、半监督学习和迁移学习。
英文摘要：
We introduce Consistent Assignment for Representation Learning (CARL), an unsupervised learning method to learn visual representations by combining ideas from self-supervised contrastive learning and deep clustering. By viewing contrastive learning from a clustering perspective, CARL learns unsupervised representations by learning a set of general prototypes that serve as energy anchors to enforce different views of a given image to be assigned to the same prototype. Unlike contemporary work on contrastive learning with deep clustering, CARL proposes to learn the set of general prototypes in an online fashion, using gradient descent without the necessity of using non-differentiable algorithms or K-Means to solve the cluster assignment problem. CARL surpasses its competitors in many representations learning benchmarks, including linear evaluation, semi-supervised learning, and transfer learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
