期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 51, 期 12, 页码 5883-5896出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2019.2959403
关键词
Task analysis; Measurement; Face recognition; Gallium nitride; Cybernetics; Blood; Training; Adversarial loss (AL); convolutional neural networks (CNNs); kinship verification; maximum mean discrepancy (MMD)
类别
资金
- National Science Fund of China [61771079]
- Chongqing Youth Talent Program
- NSFC [61732011]
- Fundamental Research Funds of Chongqing [cstc2018jcyjAX0250]
This article proposes an AdvKin method based on family ID for discriminative kin features in both small-scale and large-scale kinship verification, with the advantages of self-adversarial mechanism, pairwise contrastive loss, family ID-based softmax loss, two-stream network architecture with residual connections, and ensemble of patch-wise AdvKin networks. Extensive experiments show the superiority of the proposed AdvKin model over other state-of-the-art approaches on multiple datasets.
Kinship verification in the wild is an interesting and challenging problem. The goal of kinship verification is to determine whether a pair of faces are blood relatives or not. Most previous methods for kinship verification can be divided as handcrafted features-based shallow learning methods and convolutional neural network (CNN)-based deep-learning methods. Nevertheless, these methods are still facing the challenging task of recognizing kinship cues from facial images. The reason is that the family ID information and the distribution difference of pairwise kin-faces are rarely considered in kinship verification tasks. To this end, a family ID-based adversarial convolutional network (AdvKin) method focused on discriminative Kin features is proposed for both small-scale and large-scale kinship verification in this article. The merits of this article are four-fold: 1) for kin-relation discovery, a simple yet effective self-adversarial mechanism based on a negative maximum mean discrepancy (NMMD) loss is formulated as attacks in the first fully connected layer; 2) a pairwise contrastive loss and family ID-based softmax loss are jointly formulated in the second and third fully connected layer, respectively, for supervised training; 3) a two-stream network architecture with residual connections is proposed in AdvKin; and 4) for more fine-grained deep kin-feature augmentation, an ensemble of patch-wise AdvKin networks is proposed (E-AdvKin). Extensive experiments on 4 small-scale benchmark KinFace datasets and 1 large-scale families in the wild (FIW) dataset from the first Large-Scale Kinship Recognition Data Challenge, show the superiority of our proposed AdvKin model over other state-of-the-art approaches.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据