Face clustering is an essential tool for exploiting the unlabeled face data, and has a wide range of applications including face annotation and retrieval. Recent works show that supervised clustering can result in noticeable performance gain. However, they usually involve heuristic steps and require numerous overlapped subgraphs, severely restricting their accuracy and efficiency. In this paper, we propose a fully learnable clustering framework without requiring a large number of overlapped subgraphs. Instead, we transform the clustering problem into two sub-problems. Specifically, two graph convolutional networks, named GCN-V and GCN-E, are designed to estimate the confidence of vertices and the connectivity of edges, respectively. With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters. Experiments on two large-scale benchmarks show that our method significantly improves clustering accuracy and thus performance of the recognition models trained on top, yet it is an order of magnitude more efficient than existing supervised methods.
翻译:脸组是一个利用未贴标签的面部数据的基本工具, 并具有广泛的应用, 包括面部说明和检索。 最近的工作显示, 受监督的群集可以带来显著的性能增益。 但是, 它们通常涉及累进步骤, 需要大量重叠的子集层, 严重限制了它们的准确性和效率 。 在本文中, 我们提议一个完全可以学习的群集框架, 不需要大量重叠的子集层。 相反, 我们把群集问题转换成两个子问题 。 具体地说, 两个名为 GCN- V 和 GCN- E 的图形群集网络, 旨在分别估计脊椎的信心和边缘的连通性。 随着顶端的自信和边缘连接性, 我们自然可以在亲近性图上组织更相关的脊椎, 并将其分组。 在两个大型基准上进行的实验表明, 我们的方法大大改进了群集的准确性, 从而提高了在顶部培训的识别模型的性能。 但是, 它比现有的监督方法更有效率, 。