Graph-Based Kinship Reasoning Network

In this paper, we propose a graph-based kinship reasoning (GKR) network for kinship verification, which aims to effectively perform relational reasoning on the extracted features of an image pair. Unlike most existing methods which mainly focus on how to learn discriminative features, our method considers how to compare and fuse the extracted feature pair to reason about the kin relations. The proposed GKR constructs a star graph called kinship relational graph where each peripheral node represents the information comparison in one feature dimension and the central node is used as a bridge for information communication among peripheral nodes. Then the GKR performs relational reasoning on this graph with recursive message passing. Extensive experimental results on the KinFaceW-I and KinFaceW-II datasets show that the proposed GKR outperforms the state-of-the-art methods.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Jiwen Lu,et al.  Neighborhood repulsed metric learning for kinship verification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Cordelia Schmid,et al.  Relational Action Forecasting , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Haibin Yan,et al.  Learning discriminative compact binary face descriptor for kinship verification , 2019, Pattern Recognit. Lett..

[5]  Afshin Dehghan,et al.  Who Do I Look Like? Determining Parent-Offspring Resemblance via Gated Autoencoders , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Guodong Guo,et al.  Learning deep compact similarity metric for kinship verification from face images , 2019, Inf. Fusion.

[7]  Jiwen Lu,et al.  Gabor-based gradient orientation pyramid for kinship verification under uncontrolled environments , 2012, ACM Multimedia.

[8]  Jiwen Lu,et al.  Discriminative Multimetric Learning for Kinship Verification , 2014, IEEE Transactions on Information Forensics and Security.

[9]  Qinghua Hu,et al.  Weighted Graph Embedding-Based Metric Learning for Kinship Verification , 2019, IEEE Transactions on Image Processing.

[10]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[11]  L. Maloney,et al.  Lateralization of kin recognition signals in the human face. , 2010, Journal of vision.

[12]  Ling Shao,et al.  Learning a Multiple Kernel Similarity Metric for kinship verification , 2018, Inf. Sci..

[13]  Shahar Mahpod,et al.  Kinship verification using multiview hybrid distance learning , 2017, Comput. Vis. Image Underst..

[14]  Jiwen Lu,et al.  Discriminative Deep Metric Learning for Face and Kinship Verification , 2017, IEEE Transactions on Image Processing.

[15]  Bhiksha Raj,et al.  SphereFace: Deep Hypersphere Embedding for Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Hamdi Dibeklioglu,et al.  Visual Transformation Aided Contrastive Learning for Video-Based Kinship Verification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[17]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[18]  Liang Wang,et al.  Kinship Verification with Deep Convolutional Neural Networks , 2015, BMVC.

[19]  Jiwen Lu,et al.  BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Tsuhan Chen,et al.  Towards computational models of kinship verification , 2010, 2010 IEEE International Conference on Image Processing.