Learning to Cluster Faces via Confidence and Connectivity Estimation
This work addresses the need for more accurate and efficient face clustering, which is essential for applications like face annotation and retrieval, though it appears incremental as it builds on recent supervised clustering approaches.
The paper tackles the problem of supervised face clustering by proposing a fully learnable framework that avoids heuristic steps and numerous overlapped subgraphs, resulting in significantly improved clustering accuracy and an order of magnitude greater efficiency compared to existing methods.
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.