Structure-Aware Face Clustering on a Large-Scale Graph with 107 Nodes

Shuai Shen   Wanhua Li   Zheng Zhu   Guan Huang   Dalong Du   Jiwen Lu   Jie Zhou  

Tsinghua University       XForwardAI

CVPR 2021

[Paper] [arXiv]


Face clustering is a promising method for annotating unlabeled face images. Recent supervised approaches have boosted the face clustering accuracy greatly, however their performance is still far from satisfactory. These methods can be roughly divided into global-based and local-based ones. Global-based methods suffer from the limitation of training data scale, while local-based ones are difficult to grasp the whole graph structure information and usually take a long time for inference. Previous approaches fail to tackle these two challenges simultaneously. To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method. Specifically, we design a structure-preserved subgraph sampling strategy to explore the power of large-scale training data, which can increase the training data scale from 105 to 107. During inference, the STAR-FC performs efficient full-graph clustering with two steps: graph parsing and graph refinement. And the concept of node intimacy is introduced in the second step to mine the local structural information. The STAR-FC gets 91.97 pairwise F-score on partial MS1M within 310s which surpasses the state-of-the-arts. Furthermore, we are the first to train on very large-scale graph with 20M nodes, and achieve superior inference results on 12M testing data. Overall, as a simple and effective method, the proposed STAR-FC provides a strong baseline for large-scale face clustering.

paper thumbnail




Shuai Shen, Wanhua Li, Zheng Zhu, Guan Huan, Dalong Du, Jiwen Lu, Jie Zhou. "Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes."
In CVPR, 2021. Bibtex


The code is available at here.


Website Template