Linkage Based Face Clustering via Graph Convolution Network

被引:136
作者
Wang, Zhongdao [1 ]
Zheng, Liang [2 ]
Li, Yali [1 ]
Wang, Shengjin [1 ]
机构
[1] Tsinghua Univ, Dept Elect Engn, Beijing, Peoples R China
[2] Australian Natl Univ, Australian Ctr Robot Vis, Canberra, ACT, Australia
来源
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) | 2019年
基金
中国国家自然科学基金;
关键词
PREDICTION;
D O I
10.1109/CVPR.2019.00121
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we present an accurate and scalable approach to the face clustering task. We aim at grouping a set of faces by their potential identities. We formulate this task as a link prediction problem: a link exists between two faces if they are of the same identity. The key idea is that we find the local context in the feature space around an instance (face) contains rich information about the linkage relationship between this instance and its neighbors. By constructing sub-graphs around each instance as input data, which depict the local context, we utilize the graph convolution network (GCN) to perform reasoning and infer the likelihood of linkage between pairs in the sub-graphs. Experiments show that our method is more robust to the complex distribution of faces than conventional methods, yielding favorably comparable results to state-of-the-art methods on standard face clustering benchmarks, and is scalable to large datasets. Furthermore, we show that the proposed method does not need the number of clusters as prior, is aware of noises and outliers, and can be extended to a multi-view version for more accurate clustering accuracy.
引用
收藏
页码:1117 / +
页数:9
相关论文
共 38 条
  • [1] Friends and neighbors on the Web
    Adamic, LA
    Adar, E
    [J]. SOCIAL NETWORKS, 2003, 25 (03) : 211 - 230
  • [2] A comparison of extrinsic clustering evaluation metrics based on formal constraints
    Amigo, Enrique
    Gonzalo, Julio
    Artiles, Javier
    Verdejo, Felisa
    [J]. INFORMATION RETRIEVAL, 2009, 12 (04): : 461 - 486
  • [3] Emergence of scaling in random networks
    Barabási, AL
    Albert, R
    [J]. SCIENCE, 1999, 286 (5439) : 509 - 512
  • [4] The anatomy of a large-scale hypertextual Web search engine
    Brin, S
    Page, L
    [J]. COMPUTER NETWORKS AND ISDN SYSTEMS, 1998, 30 (1-7): : 107 - 117
  • [5] Bruna J., 2014, 2 INT C LEARN REPR, P1
  • [6] Chung Joon Son, 2018, P INTERSPEECH, DOI DOI 10.21437/INTERSPEECH.2018-1929
  • [7] Defferrard M., 2016, Advances in Neural Information Processing Systems, DOI DOI 10.5555/3157382.3157527
  • [8] Deng J., 2018, ARXIV180107698
  • [9] Ester M., 1996, KDD
  • [10] Clustering by passing messages between data points
    Frey, Brendan J.
    Dueck, Delbert
    [J]. SCIENCE, 2007, 315 (5814) : 972 - 976