用图神经网络提升亲属关系验证准确率，效果接近联合表示方法。
Kinship Verification through a Forest Neural Network
- 引入图神经网络融合人脸特征，无需从头学习联合表示。
- 在KinFaceW-II上平均提升1.6分，接近当前最佳结果。
- 渐进式引入中心损失，提升模型稳定性与泛化能力。
早期方法使用单独的人脸表征进行亲属关系验证，其准确性低于从零开始学习的父母与子女面部图像联合表征方法。本文提出一种结合图神经网络思想的方法，利用人脸表征，取得了与联合表征算法相当的效果。我们设计了分类模块结构，并引入一种新的损失组合策略，实现中心损失在训练过程中的渐进式应用。我们在KinFaceW-I和KinFaceW-II数据集上进行了实验，结果表明该方法有效：在KinFaceW-II上实现了最佳性能，所有亲属类型平均提升近1.6分；在KinFaceW-I上也接近最优表现。代码已公开于https://github.com/ali-nazari/Kinship-Verification。
原文摘要 · Abstract (English)
Early methods used face representations in kinship verification, which are less accurate than joint representations of parents' and children's facial images learned from scratch. We propose an approach featuring graph neural network concepts to utilize face representations and have comparable results to joint representation algorithms. Moreover, we designed the structure of the classification module and introduced a new combination of losses to engage the center loss gradually in training our network. Additionally, we conducted experiments on KinFaceW-I and II, demonstrating the effectiveness of our approach. We achieved the best result on KinFaceW-II, an average improvement of nearly 1.6 for all kinship types, and we were near the best on KinFaceW-I. The code is available at https://github.com/ali-nazari/Kinship-Verification
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。