你永远不会单独集群
You Never Cluster Alone
摘要：
具有实例级对比目标的自监督学习的最新进展促进了无监督聚类。然而，独立的数据不感知整体集群的上下文，并且可能经历次优分配。在本文中，我们将主流的对比学习范式扩展到一个聚类级别的方案，其中所有的数据受到相同的集群有助于一个统一的表示，编码每个数据组的上下文。然后，使用这种表示的对比学习奖励每个数据的分配。为了实现这一愿景，我们提出了双对比度聚类（TCC）。我们定义了一组分类变量作为聚类分配置信度，它将实例级学习轨迹与聚类级学习轨迹联系起来。一方面，通过相应的赋值变量作为权重，沿数据点的加权聚集实现了聚类的集合表示。我们进一步提出启发式集群增强等价物，使集群级对比学习。另一方面，我们推导了实例级对比目标的证据下界。通过重新参数化分配变量，TCC是端到端训练的，不需要交替步骤。大量的实验表明，TCC优于国家的最先进的挑战性的基准。
英文摘要：
Recent advances in self-supervised learning with instance-level contrastive objectives facilitate unsupervised clustering. However, a standalone datum is not perceiving the context of the holistic cluster, and may undergo sub-optimal assignment. In this paper, we extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation that encodes the context of each data group. Contrastive learning with this representation then rewards the assignment of each datum. To implement this vision, we propose twin-contrast clustering (TCC). We define a set of categorical variables as clustering assignment confidence, which links the instance-level learning track with the cluster-level one. On one hand, with the corresponding assignment variables being the weight, a weighted aggregation along the data points implements the set representation of a cluster. We further propose heuristic cluster augmentation equivalents to enable cluster-level contrastive learning. On the other hand, we derive the evidence lower-bound of the instance-level contrastive objective with the assignments. By reparametrizing the assignment variables, TCC is trained end-to-end, requiring no alternating steps. Extensive experiments show that TCC outperforms the state-of-the-art on challenging benchmarks.
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。
