Learning to Cluster Faces on an Affinity Graph

Lei Yang1      Xiaohang Zhan1      Dapeng Chen2      Junjie Yan2      Chen Change Loy3      Dahua Lin1
1CUHK - SenseTime Joint Lab, The Chinese University of Hong Kong
2SenseTime Group Limited, 3Nanyang Technological University
Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR 2019)

Abstract


Face recognition sees remarkable progress in recent years, and its performance has reached a very high level. Taking it to a next level requires substantially larger data, which would involve prohibitive annotation cost. Hence, exploiting unlabeled data becomes an appealing alternative. Recent works have shown that clustering unlabeled faces is a promising approach, often leading to notable performance gains. Yet, how to effectively cluster, especially on a large-scale (i.e. million-level or above) dataset, remains an open question. A key challenge lies in the complex variations of cluster patterns, which make it difficult for conventional clustering methods to meet the needed accuracy. This work explores a novel approach, namely, learning to cluster instead of relying on hand-crafted criteria. Specifically, we propose a framework based on graph convolutional network, which combines a detection and a segmentation module to pinpoint face clusters. Experiments show that our method yields significantly more accurate face clusters, which, as a result, also lead to further performance gain in face recognition.

Materials



Paper


Poster

Code and Models



Codes

Public Video

Presentation



Video Recording


Slides

Related Publication

Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition. Xiaohang Zhan, Ziwei Liu, Junjie Yan, Dahua Lin, Chen Change Loy. In Proceedings of European Conference on Computer Vision (ECCV), 2018 [PDF] [Project Page] [Code]

Citation

@inproceedings{yang2019learning,
  title={Learning to Cluster Faces on an Affinity Graph},
  author={Yang, Lei and Zhan, Xiaohang and Chen, Dapeng and Yan, Junjie and Loy, Chen Change and Lin, Dahua},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2019}
}