Graph-Based Kinship Reasoning Network

Li, Wanhua; Zhang, Yingqiang; Lv, Kangchen; Lu, Jiwen; Feng, Jianjiang; Zhou, Jie

doi:10.1109/icme46284.2020.9102823

Cited by 21 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph Convolutional Networks (GCNs) [4,36,42,45] extend the convolution idea of CNNs [5,22,34] to process non-Euclidean structured data. GCNs have shown impressive capability on various tasks [2,21,24,25,47,48]. More recently, to improve GCN's ability in handling larger-scale training graph, some GCN training algorithms have been proposed.…”

Section: Related Workmentioning

confidence: 99%

Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes

Shen,

Li,

Zhu

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

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 10 5 to 10 7 . 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-thearts. Furthermore, we are the first to train on very largescale 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. Code is available at https://sstzal.github.io/STAR-FC/.

show abstract

Section: Related Workmentioning

confidence: 99%

Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes

Shen,

Li,

Zhu

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Kinship Verification: Over the past decade, a variety of approaches [8,21,26,48] have been proposed for facial kinship verification. We can categorize them into three groups [20]: hand-crafted methods, metric-learning based methods, and deep learning-based methods. In traditional exploration, hand-crafted methods have been widely used, such as histogram of the gradient [8,40,57], Gabor gradient orientation pyramid [58], self-similarity [14], and so on.…”

Section: Related Workmentioning

confidence: 99%

“…Recent years have witnessed the remarkable success of deep learning in computer vision, such as object detection [3,28], and face recognition [2,13]. Some researchers [20,52] applied deep learning technologies into kinship verification. For example, Zhang et al [52] extracted facial key-points features with CNNs.…”

Section: Related Workmentioning

confidence: 99%

Meta-Mining Discriminative Samples for Kinship Verification

Li¹,

Wang²,

Lu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Kinship verification aims to find out whether there is a kin relation for a given pair of facial images. Kinship verification databases are born with unbalanced data. For a database with N positive kinship pairs, we naturally obtain N (N − 1) negative pairs. How to fully utilize the limited positive pairs and mine discriminative information from sufficient negative samples for kinship verification remains an open issue. To address this problem, we propose a Discriminative Sample Meta-Mining (DSMM) approach in this paper. Unlike existing methods that usually construct a balanced dataset with fixed negative pairs, we propose to utilize all possible pairs and automatically learn discriminative information from data. Specifically, we sample an unbalanced train batch and a balanced meta-train batch for each iteration. Then we learn a meta-miner with the meta-gradient on the balanced meta-train batch. In the end, the samples in the unbalanced train batch are re-weighted by the learned meta-miner to optimize the kinship models. Experimental results on the widely used KinFaceW-I, KinFaceW-II, TSKinFace, and Cornell Kinship datasets demonstrate the effectiveness of the proposed approach.

show abstract

“…In recent years, social relationship recognition from an image has attracted increasing interest in the computer vision community [41,20,52,13]. Some early efforts to mine social information include kinship recognition [23,28,44,25], social role recognition [29,38] and occupation recognition [37,39]. Lu et al [28] proposed a neighborhood repulsed metric learning (NRML) method for kinship verification.…”

Section: Related Workmentioning

confidence: 99%

Graph-Based Social Relation Reasoning

Duan

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Human beings are fundamentally sociable -that we generally organize our social lives in terms of relations with other people. Understanding social relations from an image has great potential for intelligent systems such as social chatbots and personal assistants. In this paper, we propose a simpler, faster, and more accurate method named graph relational reasoning network (GR 2 N) for social relation recognition. Different from existing methods which process all social relations on an image independently, our method considers the paradigm of jointly inferring the relations by constructing a social relation graph. Furthermore, the proposed GR 2 N constructs several virtual relation graphs to explicitly grasp the strong logical constraints among different types of social relations. Experimental results illustrate that our method generates a reasonable and consistent social relation graph and improves the performance in both accuracy and efficiency.

show abstract

Graph-Based Kinship Reasoning Network

Cited by 21 publications

References 15 publications

Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes

Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes

Meta-Mining Discriminative Samples for Kinship Verification

Graph-Based Social Relation Reasoning

Contact Info

Product

Resources

About