Abstract
Given a pair of facial images, it is an interesting yet challenging problem to determine if there is a kin relation between them. Recent research on that topic has made encouraging progress by learning a kin similarity metric from kinship data. However, most of the existing metric learning algorithms cannot handle hard samples very well, i.e., some ambiguous test pairs cannot be well classified due to some compounding factors, such as the large age gap or gender difference between the parents and children. To address this, we propose an Adversarial Similarity Metric Learning (ASML) method in this paper. More specifically, ASML consists of two adversarial phases: confusion and discrimination. In confusion phase, ambiguous adversarial pairs are automatically generated to challenge the learned similarity metric; while in discrimination phase, the learned metric tries its best to adjust itself to distinguish both the original pairs and the generated adversarial pairs. Consequently, a robust and discriminative similarity metric can be learned by iteratively performing the two adversarial phases. Experiments on the two widely used kinship datasets demonstrate the efficacy of our proposed ASML method in comparison with the state-of-the-art metric learning solutions to kinship verification.
Highlights
Psychological research shows that individuals related by blood generally have more similar characteristics on their face appearance [1]–[5]
In [16], [25], [26], multi-metric learning was presented for kinship verification, which can jointly utilize the complementary information from multiple different features of facial images to achieve better verification performance
To address the above mentioned issues, we propose in this paper the Adversarial Similarity Metric Learning (ASML) method to achieve a more robust metric for kinship verification, which is inspired by the idea of adversarial training [27]–[29]
Summary
Psychological research shows that individuals related by blood generally have more similar characteristics on their face appearance [1]–[5]. The goal of model-based methods is to learn a discriminative distance metric which can appropriately measure the genetic similarity between one pair of face images. To address the above mentioned issues, we propose in this paper the Adversarial Similarity Metric Learning (ASML) method to achieve a more robust metric for kinship verification, which is inspired by the idea of adversarial training [27]–[29]. A number of ambiguous adversarial pairs, that is, similar negative data pairs and dissimilar positive data pairs, are generated in confusion stage which will challenge the learned metric. 2) We propose the Adversarial Similarity Metric Learning (ASML) method and develop an algorithm in a twostage iterative framework, which generates adversarial data pairs to facilitate learning a more robust and accurate kinship similarity metric.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
