arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.04546cs.CV
收藏

基于面部组件关系的亲属关系表征学习

Kinship Representation Learning with Face Componential Relation

Novatek Microelectronics Corp.(联咏微电子股份有限公司);NVIDIA(英伟达);National Tsing Hua University(国立清华大学);Microsoft Corp.(微软公司)

Weng-Tai Su, Min-Hung Chen, Chien-Yi Wang, Shang-Hong Lai, Trista Pei-Chun Chen

AI总结:

针对亲属关系识别中面部空间相关性利用不足的问题,提出 FaCoRNet,通过交叉注意力建模跨图像面部组件关系并自适应调整损失,在 FIW 基准上大幅超越已有方法。

摘要:

亲属关系识别旨在判断两张面部图像中的主体是亲属还是非亲属,这是一个新兴且具有挑战性的问题。然而,以往大多数方法都集中于启发式设计,而没有考虑面部图像之间的空间相关性。本文旨在学习嵌入面部组件(例如眼睛、鼻子等)之间关系信息的具有判别性的亲属关系表征。为实现这一目标,我们提出了面部组件关系网络,该网络通过交叉注意力机制学习图像之间面部组件的关系,从而自动学习对亲属关系识别重要的面部区域。此外,我们提出了面部组件关系网络(FaCoRNet),它根据来自交叉注意力的引导调整损失函数,以学习更具判别性的特征表征。所提出的 FaCoRNet 在最大的公开亲属关系识别 FIW 基准上以大幅优势优于以往的最先进方法。

英文摘要:

Kinship recognition aims to determine whether the subjects in two facial images are kin or non-kin, which is an emerging and challenging problem. However, most previous methods focus on heuristic designs without considering the spatial correlation between face images. In this paper, we aim to learn discriminative kinship representations embedded with the relation information between face components (e.g., eyes, nose, etc.). To achieve this goal, we propose the Face Componential Relation Network, which learns the relationship between face components among images with a cross-attention mechanism, which automatically learns the important facial regions for kinship recognition. Moreover, we propose Face Componential Relation Network (FaCoRNet), which adapts the loss function by the guidance from cross-attention to learn more discriminative feature representations. The proposed FaCoRNet outperforms previous state-of-the-art methods by large margins for the largest public kinship recognition FIW benchmark.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑